Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3600 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1291. Min Range: -9.1291
Max Act: 9.1291. Min Act: -0.1700
Data Index: 5004846 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1291. Min Range: -9.1291
Max Act: 8.9416. Min Act: -0.1700
Data Index: 5737781 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1291. Min Range: -9.1291
Max Act: 8.8166. Min Act: -0.1700
Data Index: 263611 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1291. Min Range: -9.1291
Max Act: 8.7541. Min Act: -0.1700
Data Index: 4662665 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1291. Min Range: -9.1291
Max Act: 8.6291. Min Act: -0.1700
Data Index: 4907352 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1291. Min Range: -9.1291
Max Act: 8.5666. Min Act: -0.1700
Data Index: 3646982 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1291. Min Range: -9.1291
Max Act: 8.5666. Min Act: -0.1700
Data Index: 3925875 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1291. Min Range: -9.1291
Max Act: 8.5041. Min Act: -0.1700
Data Index: 7385547 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1291. Min Range: -9.1291
Max Act: 8.5041. Min Act: -0.1700
Data Index: 1506577 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1291. Min Range: -9.1291
Max Act: 8.5041. Min Act: -0.1700
Data Index: 5167312 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1291. Min Range: -9.1291
Max Act: 8.5041. Min Act: -0.1700
Data Index: 7302021 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1291. Min Range: -9.1291
Max Act: 8.4416. Min Act: -0.1700
Data Index: 4570422 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1291. Min Range: -9.1291
Max Act: 8.5666. Min Act: -0.1700
Data Index: 6055682 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1291. Min Range: -9.1291
Max Act: 8.5041. Min Act: -0.1700
Data Index: 6864633 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1291. Min Range: -9.1291
Max Act: 8.4416. Min Act: -0.1700
Data Index: 62774 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1291. Min Range: -9.1291
Max Act: 8.4416. Min Act: -0.1700
Data Index: 811300 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1291. Min Range: -9.1291
Max Act: 8.4416. Min Act: -0.1700
Data Index: 79353 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1291. Min Range: -9.1291
Max Act: 8.4416. Min Act: -0.1700
Data Index: 3681863 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1291. Min Range: -9.1291
Max Act: 8.4416. Min Act: -0.1700
Data Index: 8315540 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1291. Min Range: -9.1291
Max Act: 8.3791. Min Act: -0.1700
Data Index: 2916790 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19