Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5310 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.6523. Min Act: -0.1700
Data Index: 7100160 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.6523. Min Act: -0.1700
Data Index: 3177491 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.5586. Min Act: -0.1700
Data Index: 885612 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.4648. Min Act: -0.1700
Data Index: 6086262 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.3711. Min Act: -0.1700
Data Index: 3261739 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.3711. Min Act: -0.1700
Data Index: 1169190 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.3398. Min Act: -0.1700
Data Index: 5362539 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.3398. Min Act: -0.1700
Data Index: 1000527 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.2773. Min Act: -0.1700
Data Index: 3589439 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.2773. Min Act: -0.1700
Data Index: 4173956 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.2461. Min Act: -0.1700
Data Index: 8713488 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.2461. Min Act: -0.1700
Data Index: 7521249 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.2461. Min Act: -0.1700
Data Index: 6088248 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.2148. Min Act: -0.1700
Data Index: 6905011 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.2148. Min Act: -0.1700
Data Index: 6972840 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.1836. Min Act: -0.1700
Data Index: 6055897 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.1836. Min Act: -0.1700
Data Index: 28693 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.1836. Min Act: -0.1700
Data Index: 6377913 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.1523. Min Act: -0.1700
Data Index: 4939317 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6523. Min Range: -7.6523
Max Act: 7.1836. Min Act: -0.1700
Data Index: 3004547 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19