Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2830 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.4227. Min Act: -0.1700
Data Index: 7872588 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.3602. Min Act: -0.1700
Data Index: 2444128 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.3289. Min Act: -0.1700
Data Index: 4295985 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.2664. Min Act: -0.1700
Data Index: 3381049 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.0789. Min Act: -0.1700
Data Index: 1023351 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.1414. Min Act: -0.1700
Data Index: 212273 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.0477. Min Act: -0.1700
Data Index: 7779850 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4227. Min Range: -6.4227
Max Act: 6.0477. Min Act: -0.1700
Data Index: 2550805 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4227. Min Range: -6.4227
Max Act: 5.9539. Min Act: -0.1700
Data Index: 2303263 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4227. Min Range: -6.4227
Max Act: 5.9539. Min Act: -0.1700
Data Index: 5079414 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4227. Min Range: -6.4227
Max Act: 5.9539. Min Act: -0.1700
Data Index: 6143920 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4227. Min Range: -6.4227
Max Act: 5.8914. Min Act: -0.1700
Data Index: 6296986 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4227. Min Range: -6.4227
Max Act: 5.8914. Min Act: -0.1700
Data Index: 8342542 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4227. Min Range: -6.4227
Max Act: 5.8602. Min Act: -0.1700
Data Index: 8527426 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4227. Min Range: -6.4227
Max Act: 5.8289. Min Act: -0.1700
Data Index: 1172817 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4227. Min Range: -6.4227
Max Act: 5.8914. Min Act: -0.1700
Data Index: 8609541 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4227. Min Range: -6.4227
Max Act: 5.8602. Min Act: -0.1700
Data Index: 6189601 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4227. Min Range: -6.4227
Max Act: 5.8602. Min Act: -0.1700
Data Index: 147489 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4227. Min Range: -6.4227
Max Act: 5.8289. Min Act: -0.1700
Data Index: 2712153 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4227. Min Range: -6.4227
Max Act: 5.8289. Min Act: -0.1700
Data Index: 875829 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19