Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3511 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.9242. Min Act: -0.1700
Data Index: 8092207 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.8929. Min Act: -0.1700
Data Index: 7915072 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.8617. Min Act: -0.1700
Data Index: 1663143 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.8617. Min Act: -0.1700
Data Index: 1875614 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.8617. Min Act: -0.1700
Data Index: 2491562 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.8617. Min Act: -0.1700
Data Index: 2899440 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.8304. Min Act: -0.1700
Data Index: 5128667 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.8304. Min Act: -0.1700
Data Index: 415970 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.8304. Min Act: -0.1700
Data Index: 4147004 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.8304. Min Act: -0.1700
Data Index: 7274018 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.7991. Min Act: -0.1700
Data Index: 6795779 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.7991. Min Act: -0.1700
Data Index: 766551 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.7991. Min Act: -0.1700
Data Index: 484395 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.7991. Min Act: -0.1700
Data Index: 3078547 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.7991. Min Act: -0.1700
Data Index: 2052908 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.7991. Min Act: -0.1700
Data Index: 6768862 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.7991. Min Act: -0.1700
Data Index: 3097401 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.7991. Min Act: -0.1700
Data Index: 6190776 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.7679. Min Act: -0.1700
Data Index: 5038854 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9242. Min Range: -3.9242
Max Act: 3.7679. Min Act: -0.1700
Data Index: 243212 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19