Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1082 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.7511. Min Act: -0.1700
Data Index: 5523060 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.6885. Min Act: -0.1700
Data Index: 1693361 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.6885. Min Act: -0.1700
Data Index: 8540218 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.6885. Min Act: -0.1700
Data Index: 1878408 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.6572. Min Act: -0.1699
Data Index: 2096917 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.5633. Min Act: -0.1700
Data Index: 6537872 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.5633. Min Act: -0.1697
Data Index: 5872029 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.5320. Min Act: -0.1700
Data Index: 1205054 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.5007. Min Act: -0.1700
Data Index: 347872 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.5320. Min Act: -0.1700
Data Index: 8811273 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.5320. Min Act: -0.1700
Data Index: 8154648 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.5007. Min Act: -0.1700
Data Index: 4519845 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.4693. Min Act: -0.1700
Data Index: 3582374 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.4693. Min Act: -0.1700
Data Index: 6252505 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.4693. Min Act: -0.1700
Data Index: 5710912 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.4693. Min Act: -0.1700
Data Index: 1190516 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.4693. Min Act: -0.1700
Data Index: 3689165 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.4380. Min Act: -0.1700
Data Index: 7643716 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.4380. Min Act: -0.1700
Data Index: 4967217 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7511. Min Range: -3.7511
Max Act: 3.4380. Min Act: -0.1693
Data Index: 1997220 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19