Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3475 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7628. Min Range: -8.7628
Max Act: 8.7628. Min Act: -0.1700
Data Index: 5585838 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7628. Min Range: -8.7628
Max Act: 8.5753. Min Act: -0.1700
Data Index: 8724564 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7628. Min Range: -8.7628
Max Act: 8.2628. Min Act: -0.1700
Data Index: 4530049 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7628. Min Range: -8.7628
Max Act: 8.2003. Min Act: -0.1700
Data Index: 6097340 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7628. Min Range: -8.7628
Max Act: 8.1378. Min Act: -0.1700
Data Index: 6097337 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7628. Min Range: -8.7628
Max Act: 8.1378. Min Act: -0.1700
Data Index: 252148 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7628. Min Range: -8.7628
Max Act: 8.0753. Min Act: -0.1700
Data Index: 3925967 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7628. Min Range: -8.7628
Max Act: 8.0753. Min Act: -0.1700
Data Index: 252140 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7628. Min Range: -8.7628
Max Act: 8.0128. Min Act: -0.1700
Data Index: 769841 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7628. Min Range: -8.7628
Max Act: 8.0440. Min Act: -0.1700
Data Index: 6097338 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7628. Min Range: -8.7628
Max Act: 7.9815. Min Act: -0.1700
Data Index: 6737281 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7628. Min Range: -8.7628
Max Act: 7.9503. Min Act: -0.1700
Data Index: 2780113 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7628. Min Range: -8.7628
Max Act: 7.9815. Min Act: -0.1700
Data Index: 252145 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7628. Min Range: -8.7628
Max Act: 7.9190. Min Act: -0.1700
Data Index: 252149 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7628. Min Range: -8.7628
Max Act: 7.9503. Min Act: -0.1700
Data Index: 3925969 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7628. Min Range: -8.7628
Max Act: 7.9815. Min Act: -0.1700
Data Index: 252142 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7628. Min Range: -8.7628
Max Act: 7.9190. Min Act: -0.1700
Data Index: 3925972 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7628. Min Range: -8.7628
Max Act: 7.9190. Min Act: -0.1700
Data Index: 3194101 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7628. Min Range: -8.7628
Max Act: 7.8565. Min Act: -0.1700
Data Index: 97707 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7628. Min Range: -8.7628
Max Act: 7.8878. Min Act: -0.1700
Data Index: 6950854 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19