Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3544 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.9380. Min Act: -0.1700
Data Index: 4749551 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.9067. Min Act: -0.1700
Data Index: 8603456 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.8442. Min Act: -0.1700
Data Index: 4476159 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.8442. Min Act: -0.1700
Data Index: 7052454 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.8130. Min Act: -0.1700
Data Index: 2513318 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.8130. Min Act: -0.1700
Data Index: 8485485 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.7817. Min Act: -0.1700
Data Index: 2794967 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.6880. Min Act: -0.1700
Data Index: 8408594 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.7192. Min Act: -0.1700
Data Index: 5056201 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.6567. Min Act: -0.1700
Data Index: 7142855 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.6567. Min Act: -0.1700
Data Index: 7306463 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.6255. Min Act: -0.1700
Data Index: 3564475 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.6255. Min Act: -0.1700
Data Index: 5829870 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.5630. Min Act: -0.1700
Data Index: 2192040 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.5942. Min Act: -0.1700
Data Index: 2122329 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.5630. Min Act: -0.1700
Data Index: 5447783 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.5630. Min Act: -0.1700
Data Index: 526978 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.5630. Min Act: -0.1700
Data Index: 7374973 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.5630. Min Act: -0.1700
Data Index: 4591275 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9380. Min Range: -6.9380
Max Act: 6.5630. Min Act: -0.1700
Data Index: 235480 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19