Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3435 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3877. Min Range: -5.3877
Max Act: 5.3877. Min Act: -0.1700
Data Index: 1484224 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3877. Min Range: -5.3877
Max Act: 5.3565. Min Act: -0.1700
Data Index: 2370243 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3877. Min Range: -5.3877
Max Act: 5.3252. Min Act: -0.1700
Data Index: 3860016 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3877. Min Range: -5.3877
Max Act: 5.2002. Min Act: -0.1700
Data Index: 3094840 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3877. Min Range: -5.3877
Max Act: 5.2002. Min Act: -0.1700
Data Index: 6648668 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3877. Min Range: -5.3877
Max Act: 5.1377. Min Act: -0.1700
Data Index: 3099351 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3877. Min Range: -5.3877
Max Act: 5.0752. Min Act: -0.1700
Data Index: 319236 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3877. Min Range: -5.3877
Max Act: 5.0752. Min Act: -0.1700
Data Index: 6249092 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3877. Min Range: -5.3877
Max Act: 5.0752. Min Act: -0.1700
Data Index: 7005746 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3877. Min Range: -5.3877
Max Act: 5.0440. Min Act: -0.1700
Data Index: 2073524 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3877. Min Range: -5.3877
Max Act: 5.0440. Min Act: -0.1700
Data Index: 373460 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3877. Min Range: -5.3877
Max Act: 5.0440. Min Act: -0.1700
Data Index: 2272971 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3877. Min Range: -5.3877
Max Act: 5.0127. Min Act: -0.1700
Data Index: 1998153 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3877. Min Range: -5.3877
Max Act: 5.0127. Min Act: -0.1700
Data Index: 3703238 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3877. Min Range: -5.3877
Max Act: 5.0127. Min Act: -0.1700
Data Index: 3094852 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3877. Min Range: -5.3877
Max Act: 5.0127. Min Act: -0.1700
Data Index: 6207948 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3877. Min Range: -5.3877
Max Act: 4.9815. Min Act: -0.1700
Data Index: 5657917 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3877. Min Range: -5.3877
Max Act: 5.0127. Min Act: -0.1700
Data Index: 6249106 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3877. Min Range: -5.3877
Max Act: 5.0127. Min Act: -0.1700
Data Index: 1176529 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3877. Min Range: -5.3877
Max Act: 5.0127. Min Act: -0.1700
Data Index: 2341329 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19