Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4515 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.8929. Min Act: -0.1700
Data Index: 2872146 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.7991. Min Act: -0.1700
Data Index: 1356545 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.7679. Min Act: -0.1700
Data Index: 4021488 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.7679. Min Act: -0.1700
Data Index: 1730207 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.7366. Min Act: -0.1700
Data Index: 2330122 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.7054. Min Act: -0.1700
Data Index: 7195806 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.7054. Min Act: -0.1700
Data Index: 6257290 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.7054. Min Act: -0.1700
Data Index: 1189732 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.6429. Min Act: -0.1700
Data Index: 8506634 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.6741. Min Act: -0.1700
Data Index: 6530008 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.6741. Min Act: -0.1700
Data Index: 275064 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.6429. Min Act: -0.1700
Data Index: 8585178 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.6429. Min Act: -0.1700
Data Index: 8788915 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.5804. Min Act: -0.1700
Data Index: 7750345 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.6116. Min Act: -0.1700
Data Index: 921626 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.6116. Min Act: -0.1700
Data Index: 6159381 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.5804. Min Act: -0.1700
Data Index: 1331478 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.5491. Min Act: -0.1700
Data Index: 3084443 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.4866. Min Act: -0.1700
Data Index: 1356548 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8929. Min Range: -7.8929
Max Act: 7.5179. Min Act: -0.1700
Data Index: 1703654 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19