Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1344 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.5128. Min Act: -0.1700
Data Index: 6496185 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.5290. Min Act: -0.1700
Data Index: 5859108 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.5290. Min Act: -0.1700
Data Index: 6616665 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.5290. Min Act: -0.1700
Data Index: 7941792 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.5128. Min Act: -0.1700
Data Index: 3056328 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.4804. Min Act: -0.1700
Data Index: 5519004 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.4641. Min Act: -0.1700
Data Index: 6828541 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.4804. Min Act: -0.1700
Data Index: 1604260 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.4641. Min Act: -0.1700
Data Index: 3674147 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.4804. Min Act: -0.1700
Data Index: 3393291 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.4641. Min Act: -0.1700
Data Index: 1463319 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.4479. Min Act: -0.1700
Data Index: 5199543 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.4479. Min Act: -0.1700
Data Index: 8282512 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.4316. Min Act: -0.1700
Data Index: 7199278 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.4316. Min Act: -0.1700
Data Index: 5374356 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.4316. Min Act: -0.1700
Data Index: 3607968 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.4316. Min Act: -0.1700
Data Index: 5757164 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.4479. Min Act: -0.1700
Data Index: 5773519 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.4479. Min Act: -0.1700
Data Index: 6465821 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5290. Min Range: -2.5290
Max Act: 2.4153. Min Act: -0.1700
Data Index: 6018428 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19