Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4033 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.9322. Min Act: -0.1700
Data Index: 7509656 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.8384. Min Act: -0.1700
Data Index: 3021210 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.7759. Min Act: -0.1700
Data Index: 7889602 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.7134. Min Act: -0.1700
Data Index: 8827767 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.7134. Min Act: -0.1700
Data Index: 6931246 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.7134. Min Act: -0.1700
Data Index: 6589055 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.6822. Min Act: -0.1700
Data Index: 150968 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.6509. Min Act: -0.1700
Data Index: 6554909 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.6509. Min Act: -0.1700
Data Index: 3875471 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.6197. Min Act: -0.1700
Data Index: 1379698 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.6197. Min Act: -0.1700
Data Index: 5646418 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.5884. Min Act: -0.1700
Data Index: 2922382 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.5572. Min Act: -0.1700
Data Index: 3003421 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.5884. Min Act: -0.1700
Data Index: 6999771 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.5884. Min Act: -0.1700
Data Index: 1533347 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.5884. Min Act: -0.1700
Data Index: 3074227 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.5884. Min Act: -0.1700
Data Index: 6522238 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.5259. Min Act: -0.1700
Data Index: 7146993 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.5572. Min Act: -0.1700
Data Index: 4046553 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9322. Min Range: -5.9322
Max Act: 5.5572. Min Act: -0.1700
Data Index: 675659 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19