Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3091 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.3981. Min Act: -0.1700
Data Index: 6157401 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.3510. Min Act: -0.1700
Data Index: 5076932 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.3353. Min Act: -0.1700
Data Index: 5053094 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.3353. Min Act: -0.1700
Data Index: 8310102 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.3353. Min Act: -0.1700
Data Index: 4527696 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.3353. Min Act: -0.1700
Data Index: 7067287 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.3353. Min Act: -0.1700
Data Index: 6157402 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.3353. Min Act: -0.1700
Data Index: 6330747 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.3196. Min Act: -0.1700
Data Index: 6819392 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.3196. Min Act: -0.1700
Data Index: 7020105 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.3353. Min Act: -0.1700
Data Index: 6093608 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.3196. Min Act: -0.1700
Data Index: 5842633 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.3039. Min Act: -0.1700
Data Index: 72037 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.3039. Min Act: -0.1700
Data Index: 3443625 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.3039. Min Act: -0.1700
Data Index: 7020106 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.3039. Min Act: -0.1700
Data Index: 1425735 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.3039. Min Act: -0.1700
Data Index: 6027000 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.3039. Min Act: -0.1700
Data Index: 427520 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.3039. Min Act: -0.1700
Data Index: 924108 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3981. Min Range: -3.3981
Max Act: 3.2882. Min Act: -0.1700
Data Index: 2488550 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19