Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1335 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.7236. Min Act: -0.1700
Data Index: 1372549 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.6923. Min Act: -0.1700
Data Index: 4928700 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.6454. Min Act: -0.1700
Data Index: 4581528 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.6454. Min Act: -0.1700
Data Index: 4075118 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.6141. Min Act: -0.1700
Data Index: 4490948 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.6298. Min Act: -0.1700
Data Index: 5001035 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.6141. Min Act: -0.1700
Data Index: 7042731 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.5828. Min Act: -0.1700
Data Index: 5306926 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.5828. Min Act: -0.1700
Data Index: 6358969 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.5672. Min Act: -0.1700
Data Index: 7333816 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.5828. Min Act: -0.1700
Data Index: 4186736 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.5515. Min Act: -0.1700
Data Index: 4079838 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.5358. Min Act: -0.1700
Data Index: 2696566 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.5358. Min Act: -0.1700
Data Index: 4865915 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.5515. Min Act: -0.1700
Data Index: 6471674 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.5045. Min Act: -0.1700
Data Index: 6492880 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.5202. Min Act: -0.1700
Data Index: 1711985 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.5202. Min Act: -0.1700
Data Index: 5624135 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.4889. Min Act: -0.1700
Data Index: 5532138 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7236. Min Range: -3.7236
Max Act: 3.5045. Min Act: -0.1700
Data Index: 2578496 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19