Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3035 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3396. Min Range: -6.3396
Max Act: 6.3396. Min Act: -0.1700
Data Index: 5668649 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3396. Min Range: -6.3396
Max Act: 6.1208. Min Act: -0.1700
Data Index: 2907615 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3396. Min Range: -6.3396
Max Act: 6.1521. Min Act: -0.1700
Data Index: 6773905 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3396. Min Range: -6.3396
Max Act: 6.1521. Min Act: -0.1700
Data Index: 7525979 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3396. Min Range: -6.3396
Max Act: 6.0896. Min Act: -0.1700
Data Index: 6487531 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3396. Min Range: -6.3396
Max Act: 6.0896. Min Act: -0.1700
Data Index: 3475996 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3396. Min Range: -6.3396
Max Act: 6.0583. Min Act: -0.1700
Data Index: 4156349 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3396. Min Range: -6.3396
Max Act: 6.0583. Min Act: -0.1700
Data Index: 3647850 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3396. Min Range: -6.3396
Max Act: 6.0271. Min Act: -0.1700
Data Index: 3679253 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3396. Min Range: -6.3396
Max Act: 5.9958. Min Act: -0.1700
Data Index: 509698 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3396. Min Range: -6.3396
Max Act: 6.0271. Min Act: -0.1700
Data Index: 6180106 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3396. Min Range: -6.3396
Max Act: 5.9958. Min Act: -0.1700
Data Index: 4672772 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3396. Min Range: -6.3396
Max Act: 5.9958. Min Act: -0.1700
Data Index: 2518640 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3396. Min Range: -6.3396
Max Act: 5.9958. Min Act: -0.1700
Data Index: 1322774 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3396. Min Range: -6.3396
Max Act: 5.9958. Min Act: -0.1700
Data Index: 3187537 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3396. Min Range: -6.3396
Max Act: 5.9958. Min Act: -0.1700
Data Index: 3177703 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3396. Min Range: -6.3396
Max Act: 5.9958. Min Act: -0.1700
Data Index: 3069324 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3396. Min Range: -6.3396
Max Act: 5.9958. Min Act: -0.1700
Data Index: 436567 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3396. Min Range: -6.3396
Max Act: 5.9646. Min Act: -0.1700
Data Index: 6000604 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3396. Min Range: -6.3396
Max Act: 5.9333. Min Act: -0.1700
Data Index: 2383156 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19