Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6353 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1363. Min Range: -9.1363
Max Act: 9.1363. Min Act: -0.1700
Data Index: 249413 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1363. Min Range: -9.1363
Max Act: 9.0738. Min Act: -0.1700
Data Index: 4820516 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1363. Min Range: -9.1363
Max Act: 9.0113. Min Act: -0.1700
Data Index: 1155612 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1363. Min Range: -9.1363
Max Act: 9.0113. Min Act: -0.1700
Data Index: 1151072 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1363. Min Range: -9.1363
Max Act: 9.0113. Min Act: -0.1700
Data Index: 1531606 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1363. Min Range: -9.1363
Max Act: 8.9488. Min Act: -0.1700
Data Index: 443101 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1363. Min Range: -9.1363
Max Act: 8.9488. Min Act: -0.1700
Data Index: 493832 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1363. Min Range: -9.1363
Max Act: 8.8863. Min Act: -0.1700
Data Index: 4760969 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1363. Min Range: -9.1363
Max Act: 8.8238. Min Act: -0.1700
Data Index: 4868455 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1363. Min Range: -9.1363
Max Act: 8.8238. Min Act: -0.1700
Data Index: 4251032 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1363. Min Range: -9.1363
Max Act: 8.7613. Min Act: -0.1700
Data Index: 4551395 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1363. Min Range: -9.1363
Max Act: 8.6988. Min Act: -0.1700
Data Index: 3039279 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1363. Min Range: -9.1363
Max Act: 8.8238. Min Act: -0.1700
Data Index: 4426212 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1363. Min Range: -9.1363
Max Act: 8.7613. Min Act: -0.1700
Data Index: 7936198 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1363. Min Range: -9.1363
Max Act: 8.7613. Min Act: -0.1700
Data Index: 6568300 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1363. Min Range: -9.1363
Max Act: 8.7613. Min Act: -0.1700
Data Index: 1674691 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1363. Min Range: -9.1363
Max Act: 8.8238. Min Act: -0.1700
Data Index: 6287927 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1363. Min Range: -9.1363
Max Act: 8.7613. Min Act: -0.1700
Data Index: 4086259 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1363. Min Range: -9.1363
Max Act: 8.6988. Min Act: -0.1700
Data Index: 4814175 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1363. Min Range: -9.1363
Max Act: 8.6988. Min Act: -0.1700
Data Index: 1749458 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19