Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3757 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.7338. Min Act: -0.1700
Data Index: 2878850 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.7338. Min Act: -0.1700
Data Index: 4563422 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.7025. Min Act: -0.1700
Data Index: 8272933 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.6399. Min Act: -0.1700
Data Index: 934488 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.6086. Min Act: -0.1700
Data Index: 7125957 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.5773. Min Act: -0.1700
Data Index: 2102388 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.6086. Min Act: -0.1700
Data Index: 7264413 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.5773. Min Act: -0.1700
Data Index: 7662619 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.5617. Min Act: -0.1700
Data Index: 5156631 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.5304. Min Act: -0.1700
Data Index: 681838 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.5147. Min Act: -0.1700
Data Index: 3540953 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.5304. Min Act: -0.1700
Data Index: 4196974 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.4990. Min Act: -0.1700
Data Index: 3491847 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.4990. Min Act: -0.1700
Data Index: 4434185 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.4677. Min Act: -0.1700
Data Index: 5466394 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.4834. Min Act: -0.1700
Data Index: 8218041 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.4834. Min Act: -0.1700
Data Index: 5045177 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.4990. Min Act: -0.1700
Data Index: 5730398 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.4990. Min Act: -0.1700
Data Index: 3314705 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7338. Min Range: -3.7338
Max Act: 3.4834. Min Act: -0.1700
Data Index: 5286586 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19