Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6108 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5916. Min Range: -8.5916
Max Act: 8.5916. Min Act: -0.1700
Data Index: 4023640 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5916. Min Range: -8.5916
Max Act: 8.4041. Min Act: -0.1700
Data Index: 335647 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5916. Min Range: -8.5916
Max Act: 8.2166. Min Act: -0.1699
Data Index: 7793372 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5916. Min Range: -8.5916
Max Act: 8.0916. Min Act: -0.1700
Data Index: 3719391 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5916. Min Range: -8.5916
Max Act: 8.1541. Min Act: -0.1700
Data Index: 6498300 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5916. Min Range: -8.5916
Max Act: 8.0291. Min Act: -0.1700
Data Index: 6616562 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5916. Min Range: -8.5916
Max Act: 8.0291. Min Act: -0.1700
Data Index: 7503333 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5916. Min Range: -8.5916
Max Act: 8.0291. Min Act: -0.1700
Data Index: 7034129 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5916. Min Range: -8.5916
Max Act: 8.0291. Min Act: -0.1700
Data Index: 4201567 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5916. Min Range: -8.5916
Max Act: 8.0291. Min Act: -0.1700
Data Index: 4523327 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5916. Min Range: -8.5916
Max Act: 8.0291. Min Act: -0.1700
Data Index: 3538155 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5916. Min Range: -8.5916
Max Act: 7.9666. Min Act: -0.1700
Data Index: 8282789 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5916. Min Range: -8.5916
Max Act: 7.9666. Min Act: -0.1700
Data Index: 2999452 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5916. Min Range: -8.5916
Max Act: 7.9666. Min Act: -0.1700
Data Index: 1890984 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5916. Min Range: -8.5916
Max Act: 7.9041. Min Act: -0.1700
Data Index: 4542910 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5916. Min Range: -8.5916
Max Act: 7.9041. Min Act: -0.1700
Data Index: 6830579 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5916. Min Range: -8.5916
Max Act: 7.9041. Min Act: -0.1700
Data Index: 8432407 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5916. Min Range: -8.5916
Max Act: 7.9041. Min Act: -0.1700
Data Index: 6134048 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5916. Min Range: -8.5916
Max Act: 7.8416. Min Act: -0.1700
Data Index: 2584827 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5916. Min Range: -8.5916
Max Act: 7.9041. Min Act: -0.1700
Data Index: 6104605 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19