Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3263 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.8755. Min Act: -0.1700
Data Index: 7700292 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.7818. Min Act: -0.1700
Data Index: 11838 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.6880. Min Act: -0.1700
Data Index: 15962 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.6880. Min Act: -0.1700
Data Index: 594295 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.6880. Min Act: -0.1700
Data Index: 2422938 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.6255. Min Act: -0.1700
Data Index: 8159628 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.5943. Min Act: -0.1700
Data Index: 12598 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.5943. Min Act: -0.1700
Data Index: 3444777 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.5630. Min Act: -0.1700
Data Index: 1411540 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.5630. Min Act: -0.1700
Data Index: 3983424 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.5318. Min Act: -0.1700
Data Index: 7903210 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.5630. Min Act: -0.1700
Data Index: 3762851 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.5318. Min Act: -0.1700
Data Index: 4537522 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.5005. Min Act: -0.1700
Data Index: 3446347 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.5005. Min Act: -0.1700
Data Index: 2605377 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.4693. Min Act: -0.1700
Data Index: 7231665 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.4693. Min Act: -0.1700
Data Index: 5192080 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.4693. Min Act: -0.1700
Data Index: 3209362 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.4380. Min Act: -0.1700
Data Index: 6556585 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8755. Min Range: -4.8755
Max Act: 4.4068. Min Act: -0.1700
Data Index: 6363866 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19