Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2636 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1241. Min Range: -7.1241
Max Act: 7.1241. Min Act: -0.1700
Data Index: 7224246 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1241. Min Range: -7.1241
Max Act: 6.7178. Min Act: -0.1700
Data Index: 7561905 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1241. Min Range: -7.1241
Max Act: 6.6866. Min Act: -0.1700
Data Index: 1973861 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1241. Min Range: -7.1241
Max Act: 6.6553. Min Act: -0.1700
Data Index: 6228475 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1241. Min Range: -7.1241
Max Act: 6.6553. Min Act: -0.1700
Data Index: 8703988 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1241. Min Range: -7.1241
Max Act: 6.5928. Min Act: -0.1700
Data Index: 6823645 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1241. Min Range: -7.1241
Max Act: 6.6241. Min Act: -0.1700
Data Index: 1166762 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1241. Min Range: -7.1241
Max Act: 6.5303. Min Act: -0.1700
Data Index: 6880014 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1241. Min Range: -7.1241
Max Act: 6.5303. Min Act: -0.1700
Data Index: 4861266 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1241. Min Range: -7.1241
Max Act: 6.4991. Min Act: -0.1700
Data Index: 272337 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1241. Min Range: -7.1241
Max Act: 6.5303. Min Act: -0.1700
Data Index: 2624588 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1241. Min Range: -7.1241
Max Act: 6.4991. Min Act: -0.1700
Data Index: 8641512 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1241. Min Range: -7.1241
Max Act: 6.4678. Min Act: -0.1700
Data Index: 2194100 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1241. Min Range: -7.1241
Max Act: 6.4366. Min Act: -0.1700
Data Index: 4348102 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1241. Min Range: -7.1241
Max Act: 6.4678. Min Act: -0.1700
Data Index: 3722356 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1241. Min Range: -7.1241
Max Act: 6.4366. Min Act: -0.1700
Data Index: 6377715 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1241. Min Range: -7.1241
Max Act: 6.4366. Min Act: -0.1700
Data Index: 2892317 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1241. Min Range: -7.1241
Max Act: 6.4053. Min Act: -0.1700
Data Index: 4535017 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1241. Min Range: -7.1241
Max Act: 6.4053. Min Act: -0.1700
Data Index: 6214415 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1241. Min Range: -7.1241
Max Act: 6.3428. Min Act: -0.1700
Data Index: 1956462 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19