Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4768 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.2486. Min Act: -0.1700
Data Index: 6182897 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.1857. Min Act: -0.1700
Data Index: 1153196 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.1857. Min Act: -0.1700
Data Index: 3056159 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.1385. Min Act: -0.1700
Data Index: 1890200 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.1385. Min Act: -0.1700
Data Index: 7919547 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.1228. Min Act: -0.1700
Data Index: 2741391 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.1228. Min Act: -0.1700
Data Index: 6186622 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.1070. Min Act: -0.1700
Data Index: 7889497 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.1070. Min Act: -0.1700
Data Index: 4869254 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.0755. Min Act: -0.1700
Data Index: 5096381 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.0755. Min Act: -0.1700
Data Index: 2297141 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.0755. Min Act: -0.1700
Data Index: 3823974 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.0597. Min Act: -0.1700
Data Index: 909342 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.0597. Min Act: -0.1700
Data Index: 5813460 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.0281. Min Act: -0.1700
Data Index: 1541507 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.0439. Min Act: -0.1700
Data Index: 899933 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.0281. Min Act: -0.1700
Data Index: 1542972 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.0439. Min Act: -0.1700
Data Index: 2366216 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.0597. Min Act: -0.1700
Data Index: 243775 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2486. Min Range: -3.2486
Max Act: 3.0439. Min Act: -0.1700
Data Index: 6487903 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19