Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4649 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.5568. Min Act: -0.1700
Data Index: 646763 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.5411. Min Act: -0.1700
Data Index: 7188006 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.5411. Min Act: -0.1700
Data Index: 7480672 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.5098. Min Act: -0.1700
Data Index: 5372340 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.5098. Min Act: -0.1700
Data Index: 7541018 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.4785. Min Act: -0.1700
Data Index: 4066270 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.4785. Min Act: -0.1700
Data Index: 7032766 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.4628. Min Act: -0.1700
Data Index: 6049240 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.4472. Min Act: -0.1700
Data Index: 3396338 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.4315. Min Act: -0.1700
Data Index: 5827171 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.4315. Min Act: -0.1700
Data Index: 5195610 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.4158. Min Act: -0.1700
Data Index: 969570 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.3688. Min Act: -0.1700
Data Index: 6049246 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.4001. Min Act: -0.1700
Data Index: 2242267 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.3845. Min Act: -0.1700
Data Index: 3041682 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.3531. Min Act: -0.1700
Data Index: 7411607 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.3531. Min Act: -0.1700
Data Index: 3620630 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.3688. Min Act: -0.1700
Data Index: 226947 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.3688. Min Act: -0.1700
Data Index: 5047416 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5568. Min Range: -3.5568
Max Act: 3.3374. Min Act: -0.1700
Data Index: 5986722 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19