Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.6978. Min Act: -0.1700
Data Index: 7528382 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.6978. Min Act: -0.1700
Data Index: 2123228 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.6978. Min Act: -0.1700
Data Index: 6490400 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.6353. Min Act: -0.1700
Data Index: 4400529 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.6353. Min Act: -0.1700
Data Index: 1936720 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.6353. Min Act: -0.1700
Data Index: 4670115 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.6353. Min Act: -0.1700
Data Index: 6735075 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.6353. Min Act: -0.1700
Data Index: 6470028 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.5728. Min Act: -0.1700
Data Index: 5528095 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.5728. Min Act: -0.1700
Data Index: 6584364 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.5415. Min Act: -0.1700
Data Index: 1258918 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.5415. Min Act: -0.1700
Data Index: 2356926 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.5728. Min Act: -0.1700
Data Index: 5429009 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.6040. Min Act: -0.1700
Data Index: 4543506 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.5415. Min Act: -0.1700
Data Index: 5356002 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.5415. Min Act: -0.1700
Data Index: 3896836 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.5103. Min Act: -0.1700
Data Index: 6380330 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.4165. Min Act: -0.1700
Data Index: 4117402 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.4165. Min Act: -0.1700
Data Index: 6157296 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6978. Min Range: -5.6978
Max Act: 5.4790. Min Act: -0.1700
Data Index: 2674122 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19