Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3122 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.7801. Min Act: -0.1700
Data Index: 7745339 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.7488. Min Act: -0.1700
Data Index: 5185861 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.6549. Min Act: -0.1700
Data Index: 2831682 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.6237. Min Act: -0.1700
Data Index: 8032707 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.6237. Min Act: -0.1700
Data Index: 8371672 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.6237. Min Act: -0.1700
Data Index: 5524768 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.6237. Min Act: -0.1700
Data Index: 7745329 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.6237. Min Act: -0.1700
Data Index: 6190727 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.6237. Min Act: -0.1700
Data Index: 7745331 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.6237. Min Act: -0.1700
Data Index: 7745332 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.6237. Min Act: -0.1700
Data Index: 6504131 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.5924. Min Act: -0.1700
Data Index: 1064632 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.5610. Min Act: -0.1700
Data Index: 7745326 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.5924. Min Act: -0.1700
Data Index: 1696777 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.5610. Min Act: -0.1700
Data Index: 4734346 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.5610. Min Act: -0.1700
Data Index: 1944243 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.5924. Min Act: -0.1700
Data Index: 434528 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.5924. Min Act: -0.1700
Data Index: 7745330 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.5610. Min Act: -0.1700
Data Index: 2564742 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7801. Min Range: -3.7801
Max Act: 3.5297. Min Act: -0.1700
Data Index: 5512541 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19