Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3182 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1742. Min Range: -6.1742
Max Act: 6.1742. Min Act: -0.1700
Data Index: 1090066 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1742. Min Range: -6.1742
Max Act: 6.1430. Min Act: -0.1700
Data Index: 2110559 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1742. Min Range: -6.1742
Max Act: 6.0805. Min Act: -0.1700
Data Index: 6164126 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1742. Min Range: -6.1742
Max Act: 6.0492. Min Act: -0.1700
Data Index: 1341873 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1742. Min Range: -6.1742
Max Act: 6.0492. Min Act: -0.1700
Data Index: 6812176 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1742. Min Range: -6.1742
Max Act: 6.0180. Min Act: -0.1700
Data Index: 2215230 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1742. Min Range: -6.1742
Max Act: 6.0180. Min Act: -0.1700
Data Index: 8228404 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1742. Min Range: -6.1742
Max Act: 5.9867. Min Act: -0.1700
Data Index: 1749230 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1742. Min Range: -6.1742
Max Act: 5.9867. Min Act: -0.1700
Data Index: 702446 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1742. Min Range: -6.1742
Max Act: 5.9555. Min Act: -0.1700
Data Index: 5874713 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1742. Min Range: -6.1742
Max Act: 5.9555. Min Act: -0.1700
Data Index: 1199633 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1742. Min Range: -6.1742
Max Act: 5.9242. Min Act: -0.1700
Data Index: 7844591 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1742. Min Range: -6.1742
Max Act: 5.9242. Min Act: -0.1700
Data Index: 4723070 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1742. Min Range: -6.1742
Max Act: 5.9242. Min Act: -0.1700
Data Index: 2696103 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1742. Min Range: -6.1742
Max Act: 5.9242. Min Act: -0.1700
Data Index: 8027519 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1742. Min Range: -6.1742
Max Act: 5.8930. Min Act: -0.1700
Data Index: 2260520 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1742. Min Range: -6.1742
Max Act: 5.9242. Min Act: -0.1700
Data Index: 945216 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1742. Min Range: -6.1742
Max Act: 5.9242. Min Act: -0.1700
Data Index: 8529048 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1742. Min Range: -6.1742
Max Act: 5.9242. Min Act: -0.1700
Data Index: 321259 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1742. Min Range: -6.1742
Max Act: 5.8930. Min Act: -0.1700
Data Index: 5066298 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19