Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 508 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1108. Min Range: -8.1108
Max Act: 8.1108. Min Act: -0.1700
Data Index: 4973167 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1108. Min Range: -8.1108
Max Act: 7.4858. Min Act: -0.1700
Data Index: 3688868 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1108. Min Range: -8.1108
Max Act: 7.3608. Min Act: -0.1700
Data Index: 5339753 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1108. Min Range: -8.1108
Max Act: 7.2983. Min Act: -0.1700
Data Index: 5975030 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1108. Min Range: -8.1108
Max Act: 7.2670. Min Act: -0.1700
Data Index: 4595069 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1108. Min Range: -8.1108
Max Act: 7.2358. Min Act: -0.1700
Data Index: 6497511 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1108. Min Range: -8.1108
Max Act: 7.1733. Min Act: -0.1700
Data Index: 7066621 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1108. Min Range: -8.1108
Max Act: 7.2045. Min Act: -0.1700
Data Index: 951336 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1108. Min Range: -8.1108
Max Act: 7.1733. Min Act: -0.1700
Data Index: 8513166 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1108. Min Range: -8.1108
Max Act: 7.1108. Min Act: -0.1700
Data Index: 3312475 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1108. Min Range: -8.1108
Max Act: 7.0483. Min Act: -0.1700
Data Index: 4886776 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1108. Min Range: -8.1108
Max Act: 7.0170. Min Act: -0.1700
Data Index: 7608842 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1108. Min Range: -8.1108
Max Act: 6.9858. Min Act: -0.1700
Data Index: 994050 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1108. Min Range: -8.1108
Max Act: 6.9233. Min Act: -0.1700
Data Index: 1319919 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1108. Min Range: -8.1108
Max Act: 6.9233. Min Act: -0.1700
Data Index: 2373979 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1108. Min Range: -8.1108
Max Act: 6.9233. Min Act: -0.1700
Data Index: 3162430 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1108. Min Range: -8.1108
Max Act: 6.8608. Min Act: -0.1700
Data Index: 7316029 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1108. Min Range: -8.1108
Max Act: 6.8295. Min Act: -0.1700
Data Index: 6293348 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1108. Min Range: -8.1108
Max Act: 6.7983. Min Act: -0.1700
Data Index: 2000555 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1108. Min Range: -8.1108
Max Act: 6.7983. Min Act: -0.1700
Data Index: 1587833 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19