Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3973 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.6357. Min Act: -0.1700
Data Index: 8155959 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.6357. Min Act: -0.1700
Data Index: 8650400 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.5107. Min Act: -0.1700
Data Index: 3699522 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.3232. Min Act: -0.1700
Data Index: 1070416 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.2607. Min Act: -0.1700
Data Index: 2184935 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.3232. Min Act: -0.1700
Data Index: 380438 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.1982. Min Act: -0.1700
Data Index: 1376133 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.1982. Min Act: -0.1700
Data Index: 3226937 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.1982. Min Act: -0.1700
Data Index: 3545830 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.1982. Min Act: -0.1700
Data Index: 1986167 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.1982. Min Act: -0.1700
Data Index: 3821625 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.0732. Min Act: -0.1700
Data Index: 6059649 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.0107. Min Act: -0.1700
Data Index: 7483284 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.0107. Min Act: -0.1700
Data Index: 926111 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.0732. Min Act: -0.1700
Data Index: 6945347 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.0732. Min Act: -0.1700
Data Index: 6347497 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.0732. Min Act: -0.1700
Data Index: 5904720 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.0107. Min Act: -0.1700
Data Index: 3907623 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.0107. Min Act: -0.1700
Data Index: 4872352 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6357. Min Range: -10.6357
Max Act: 10.0107. Min Act: -0.1700
Data Index: 7807845 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19