Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3433 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.9561. Min Act: -0.1700
Data Index: 2188355 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.9244. Min Act: -0.1700
Data Index: 2177972 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.9244. Min Act: -0.1700
Data Index: 2900650 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.9244. Min Act: -0.1700
Data Index: 1869247 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.9086. Min Act: -0.1700
Data Index: 8272076 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.9086. Min Act: -0.1700
Data Index: 2405004 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.9086. Min Act: -0.1700
Data Index: 2068833 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.9086. Min Act: -0.1700
Data Index: 4674113 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.9086. Min Act: -0.1700
Data Index: 8408046 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.9086. Min Act: -0.1700
Data Index: 4718678 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8927. Min Act: -0.1700
Data Index: 8267887 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.9086. Min Act: -0.1700
Data Index: 3572228 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.9086. Min Act: -0.1700
Data Index: 7207445 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.9086. Min Act: -0.1700
Data Index: 3454174 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.9086. Min Act: -0.1700
Data Index: 5640886 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.9086. Min Act: -0.1700
Data Index: 5490529 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.9086. Min Act: -0.1700
Data Index: 2897599 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8927. Min Act: -0.1700
Data Index: 4491586 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8927. Min Act: -0.1700
Data Index: 2070407 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8927. Min Act: -0.1696
Data Index: 2347919 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19