Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 266 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4490. Min Range: -6.4490
Max Act: 6.4490. Min Act: -0.1700
Data Index: 489535 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4490. Min Range: -6.4490
Max Act: 6.3865. Min Act: -0.1700
Data Index: 3354575 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4490. Min Range: -6.4490
Max Act: 6.2927. Min Act: -0.1700
Data Index: 3734539 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4490. Min Range: -6.4490
Max Act: 6.1677. Min Act: -0.1700
Data Index: 173069 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4490. Min Range: -6.4490
Max Act: 6.1990. Min Act: -0.1700
Data Index: 1999393 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4490. Min Range: -6.4490
Max Act: 6.1365. Min Act: -0.1700
Data Index: 828678 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4490. Min Range: -6.4490
Max Act: 6.1052. Min Act: -0.1700
Data Index: 4959083 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4490. Min Range: -6.4490
Max Act: 6.0740. Min Act: -0.1700
Data Index: 8519651 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4490. Min Range: -6.4490
Max Act: 6.0740. Min Act: -0.1700
Data Index: 6498667 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4490. Min Range: -6.4490
Max Act: 6.0427. Min Act: -0.1700
Data Index: 7178788 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4490. Min Range: -6.4490
Max Act: 6.0427. Min Act: -0.1700
Data Index: 365673 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4490. Min Range: -6.4490
Max Act: 6.0115. Min Act: -0.1699
Data Index: 5184409 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4490. Min Range: -6.4490
Max Act: 6.0115. Min Act: -0.1700
Data Index: 8365669 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4490. Min Range: -6.4490
Max Act: 6.0115. Min Act: -0.1700
Data Index: 8615952 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4490. Min Range: -6.4490
Max Act: 6.0115. Min Act: -0.1700
Data Index: 6123312 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4490. Min Range: -6.4490
Max Act: 6.0115. Min Act: -0.1700
Data Index: 5249281 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.9802. Min Act: -0.1700
Data Index: 7899539 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.9802. Min Act: -0.1700
Data Index: 6011542 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.9802. Min Act: -0.1700
Data Index: 5805948 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4490. Min Range: -6.4490
Max Act: 5.9802. Min Act: -0.1700
Data Index: 6640900 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19