Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2210 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4056. Min Range: -7.4056
Max Act: 7.4056. Min Act: -0.1700
Data Index: 3685828 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4056. Min Range: -7.4056
Max Act: 7.2493. Min Act: -0.1700
Data Index: 6109505 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4056. Min Range: -7.4056
Max Act: 6.8118. Min Act: -0.1700
Data Index: 1138975 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4056. Min Range: -7.4056
Max Act: 6.7493. Min Act: -0.1700
Data Index: 8133488 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4056. Min Range: -7.4056
Max Act: 6.7181. Min Act: -0.1700
Data Index: 6387566 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4056. Min Range: -7.4056
Max Act: 6.5618. Min Act: -0.1700
Data Index: 7209076 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4056. Min Range: -7.4056
Max Act: 6.5306. Min Act: -0.1700
Data Index: 7968445 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4056. Min Range: -7.4056
Max Act: 6.4368. Min Act: -0.1700
Data Index: 1459645 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4056. Min Range: -7.4056
Max Act: 6.4368. Min Act: -0.1700
Data Index: 287242 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4056. Min Range: -7.4056
Max Act: 6.4056. Min Act: -0.1700
Data Index: 2152027 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4056. Min Range: -7.4056
Max Act: 6.3743. Min Act: -0.1700
Data Index: 4216007 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4056. Min Range: -7.4056
Max Act: 6.3743. Min Act: -0.1700
Data Index: 1113674 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4056. Min Range: -7.4056
Max Act: 6.3743. Min Act: -0.1700
Data Index: 8608268 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4056. Min Range: -7.4056
Max Act: 6.3743. Min Act: -0.1700
Data Index: 7499159 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4056. Min Range: -7.4056
Max Act: 6.3743. Min Act: -0.1700
Data Index: 5061080 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4056. Min Range: -7.4056
Max Act: 6.3743. Min Act: -0.1700
Data Index: 6779284 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4056. Min Range: -7.4056
Max Act: 6.3431. Min Act: -0.1700
Data Index: 6729242 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4056. Min Range: -7.4056
Max Act: 6.3118. Min Act: -0.1700
Data Index: 2127928 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4056. Min Range: -7.4056
Max Act: 6.3118. Min Act: -0.1700
Data Index: 7049506 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4056. Min Range: -7.4056
Max Act: 6.3118. Min Act: -0.1700
Data Index: 961974 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19