Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5297 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.3369. Min Act: -0.1700
Data Index: 3612309 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.2744. Min Act: -0.1700
Data Index: 3934343 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.1806. Min Act: -0.1700
Data Index: 4578717 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.1494. Min Act: -0.1700
Data Index: 1603201 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.1494. Min Act: -0.1700
Data Index: 2163110 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.1806. Min Act: -0.1700
Data Index: 2584458 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.1181. Min Act: -0.1700
Data Index: 2596666 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.1181. Min Act: -0.1700
Data Index: 8670136 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.1181. Min Act: -0.1700
Data Index: 7084921 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.0869. Min Act: -0.1700
Data Index: 3887917 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.0869. Min Act: -0.1700
Data Index: 4347106 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.0869. Min Act: -0.1700
Data Index: 6275483 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.0869. Min Act: -0.1700
Data Index: 4334401 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.0244. Min Act: -0.1700
Data Index: 394257 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.0556. Min Act: -0.1700
Data Index: 2792858 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.0556. Min Act: -0.1700
Data Index: 6732876 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.0556. Min Act: -0.1700
Data Index: 3224424 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.0244. Min Act: -0.1700
Data Index: 2005146 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.0244. Min Act: -0.1700
Data Index: 8631350 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3369. Min Range: -5.3369
Max Act: 5.0244. Min Act: -0.1700
Data Index: 673104 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19