Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 54 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 15.3118. Min Range: -15.3118
Max Act: 15.3118. Min Act: -0.1700
Data Index: 2311891 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.3118. Min Range: -15.3118
Max Act: 15.2493. Min Act: -0.1700
Data Index: 7948601 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.3118. Min Range: -15.3118
Max Act: 14.8118. Min Act: -0.1700
Data Index: 8632848 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.3118. Min Range: -15.3118
Max Act: 14.6868. Min Act: -0.1700
Data Index: 2244795 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.3118. Min Range: -15.3118
Max Act: 14.6868. Min Act: -0.1700
Data Index: 1881998 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.3118. Min Range: -15.3118
Max Act: 14.6868. Min Act: -0.1700
Data Index: 6158440 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.3118. Min Range: -15.3118
Max Act: 14.6243. Min Act: -0.1700
Data Index: 7290118 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.3118. Min Range: -15.3118
Max Act: 14.4368. Min Act: -0.1700
Data Index: 4737776 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.3118. Min Range: -15.3118
Max Act: 14.3118. Min Act: -0.1700
Data Index: 3923640 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.3118. Min Range: -15.3118
Max Act: 14.3743. Min Act: -0.1700
Data Index: 5785782 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.3118. Min Range: -15.3118
Max Act: 14.3118. Min Act: -0.1700
Data Index: 7184404 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.3118. Min Range: -15.3118
Max Act: 14.1868. Min Act: -0.1700
Data Index: 4442254 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.3118. Min Range: -15.3118
Max Act: 14.1243. Min Act: -0.1700
Data Index: 1670294 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.3118. Min Range: -15.3118
Max Act: 14.1868. Min Act: -0.1700
Data Index: 3982032 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.3118. Min Range: -15.3118
Max Act: 14.1243. Min Act: -0.1700
Data Index: 3983437 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.3118. Min Range: -15.3118
Max Act: 14.1243. Min Act: -0.1700
Data Index: 2573084 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.3118. Min Range: -15.3118
Max Act: 14.0618. Min Act: -0.1700
Data Index: 6829035 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.3118. Min Range: -15.3118
Max Act: 14.0618. Min Act: -0.1700
Data Index: 6457404 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.3118. Min Range: -15.3118
Max Act: 14.0618. Min Act: -0.1700
Data Index: 8114995 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.3118. Min Range: -15.3118
Max Act: 14.0618. Min Act: -0.1700
Data Index: 5722709 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19