Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3868 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.4116. Min Act: -0.1700
Data Index: 3834212 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.3179. Min Act: -0.1700
Data Index: 482532 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.2866. Min Act: -0.1700
Data Index: 3894071 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.2241. Min Act: -0.1700
Data Index: 6687136 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.1929. Min Act: -0.1700
Data Index: 627352 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.1304. Min Act: -0.1700
Data Index: 7126084 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.1304. Min Act: -0.1700
Data Index: 6878278 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.1304. Min Act: -0.1700
Data Index: 371085 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.1304. Min Act: -0.1700
Data Index: 6372851 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.0991. Min Act: -0.1700
Data Index: 7924837 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.0679. Min Act: -0.1700
Data Index: 50092 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.0366. Min Act: -0.1700
Data Index: 5613220 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.0366. Min Act: -0.1700
Data Index: 259674 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.0366. Min Act: -0.1700
Data Index: 3766190 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.0366. Min Act: -0.1700
Data Index: 3063255 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.0054. Min Act: -0.1700
Data Index: 6237087 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.0366. Min Act: -0.1700
Data Index: 1174277 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4116. Min Range: -5.4116
Max Act: 5.0054. Min Act: -0.1700
Data Index: 8402386 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4116. Min Range: -5.4116
Max Act: 4.9429. Min Act: -0.1700
Data Index: 2854183 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4116. Min Range: -5.4116
Max Act: 4.9741. Min Act: -0.1700
Data Index: 1502737 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19