Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2044 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.6587. Min Act: -0.1700
Data Index: 8317027 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.5337. Min Act: -0.1700
Data Index: 1285518 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.4712. Min Act: -0.1700
Data Index: 6967855 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.3774. Min Act: -0.1700
Data Index: 2558789 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.3462. Min Act: -0.1700
Data Index: 2909336 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.3149. Min Act: -0.1700
Data Index: 479543 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.3149. Min Act: -0.1700
Data Index: 2131304 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.2524. Min Act: -0.1700
Data Index: 360448 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.2524. Min Act: -0.1700
Data Index: 2160445 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.2524. Min Act: -0.1700
Data Index: 2028001 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.1587. Min Act: -0.1700
Data Index: 7306227 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.1587. Min Act: -0.1700
Data Index: 4516879 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.1274. Min Act: -0.1700
Data Index: 4523921 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.0649. Min Act: -0.1700
Data Index: 1202506 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.0649. Min Act: -0.1700
Data Index: 8798521 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.0649. Min Act: -0.1700
Data Index: 3250337 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.0649. Min Act: -0.1700
Data Index: 7129627 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.0337. Min Act: -0.1700
Data Index: 6062939 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.0024. Min Act: -0.1700
Data Index: 798397 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6587. Min Range: -6.6587
Max Act: 6.0024. Min Act: -0.1700
Data Index: 71105 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19