Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4810 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.7036. Min Act: -0.1700
Data Index: 7545312 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.6099. Min Act: -0.1700
Data Index: 6654310 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.5474. Min Act: -0.1700
Data Index: 1614507 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.5786. Min Act: -0.1700
Data Index: 7224613 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.5161. Min Act: -0.1700
Data Index: 2811452 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.5161. Min Act: -0.1700
Data Index: 5656992 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.4849. Min Act: -0.1700
Data Index: 4092077 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.4849. Min Act: -0.1700
Data Index: 2135032 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.4224. Min Act: -0.1700
Data Index: 5276356 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.4224. Min Act: -0.1700
Data Index: 457059 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.3599. Min Act: -0.1700
Data Index: 976807 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.3911. Min Act: -0.1700
Data Index: 8365480 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.3599. Min Act: -0.1700
Data Index: 794003 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.3599. Min Act: -0.1700
Data Index: 4736694 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.3599. Min Act: -0.1700
Data Index: 8220989 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.3286. Min Act: -0.1700
Data Index: 7079493 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.3599. Min Act: -0.1700
Data Index: 3233661 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.3599. Min Act: -0.1700
Data Index: 4363785 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.2974. Min Act: -0.1700
Data Index: 1999913 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7036. Min Range: -6.7036
Max Act: 6.2974. Min Act: -0.1700
Data Index: 8028222 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19