Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3103 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.9194. Min Act: -0.1700
Data Index: 8299888 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.7319. Min Act: -0.1700
Data Index: 695017 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.7007. Min Act: -0.1700
Data Index: 4599805 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.6694. Min Act: -0.1700
Data Index: 923962 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.6382. Min Act: -0.1700
Data Index: 5664832 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.6382. Min Act: -0.1700
Data Index: 6685459 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.6382. Min Act: -0.1700
Data Index: 6394734 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.6382. Min Act: -0.1700
Data Index: 695012 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.6382. Min Act: -0.1700
Data Index: 6676514 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.6069. Min Act: -0.1700
Data Index: 8505437 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.6069. Min Act: -0.1700
Data Index: 2120270 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.6069. Min Act: -0.1700
Data Index: 7733754 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.5757. Min Act: -0.1700
Data Index: 2015506 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.6069. Min Act: -0.1700
Data Index: 7403807 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.6069. Min Act: -0.1700
Data Index: 3167625 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.5757. Min Act: -0.1700
Data Index: 4239947 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.5757. Min Act: -0.1700
Data Index: 4060763 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.5757. Min Act: -0.1700
Data Index: 7869716 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.5757. Min Act: -0.1700
Data Index: 6086758 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9194. Min Range: -5.9194
Max Act: 5.5757. Min Act: -0.1700
Data Index: 6085879 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19