Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3596 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3067. Min Range: -7.3067
Max Act: 7.3067. Min Act: -0.1700
Data Index: 4212424 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3067. Min Range: -7.3067
Max Act: 7.2442. Min Act: -0.1700
Data Index: 1722839 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3067. Min Range: -7.3067
Max Act: 7.2442. Min Act: -0.1700
Data Index: 235243 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3067. Min Range: -7.3067
Max Act: 7.0255. Min Act: -0.1700
Data Index: 35481 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3067. Min Range: -7.3067
Max Act: 6.9005. Min Act: -0.1700
Data Index: 3753068 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3067. Min Range: -7.3067
Max Act: 6.8380. Min Act: -0.1700
Data Index: 1287398 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3067. Min Range: -7.3067
Max Act: 6.8380. Min Act: -0.1700
Data Index: 8760498 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3067. Min Range: -7.3067
Max Act: 6.8380. Min Act: -0.1700
Data Index: 5445948 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3067. Min Range: -7.3067
Max Act: 6.8067. Min Act: -0.1700
Data Index: 7480027 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3067. Min Range: -7.3067
Max Act: 6.7755. Min Act: -0.1700
Data Index: 8357516 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3067. Min Range: -7.3067
Max Act: 6.7442. Min Act: -0.1700
Data Index: 1901950 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3067. Min Range: -7.3067
Max Act: 6.7755. Min Act: -0.1700
Data Index: 8663943 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3067. Min Range: -7.3067
Max Act: 6.7442. Min Act: -0.1700
Data Index: 2346689 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3067. Min Range: -7.3067
Max Act: 6.7442. Min Act: -0.1700
Data Index: 4241722 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3067. Min Range: -7.3067
Max Act: 6.7442. Min Act: -0.1700
Data Index: 3146609 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3067. Min Range: -7.3067
Max Act: 6.7130. Min Act: -0.1700
Data Index: 4687204 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3067. Min Range: -7.3067
Max Act: 6.6817. Min Act: -0.1700
Data Index: 4057790 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3067. Min Range: -7.3067
Max Act: 6.6817. Min Act: -0.1700
Data Index: 4016408 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3067. Min Range: -7.3067
Max Act: 6.6817. Min Act: -0.1700
Data Index: 6653538 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3067. Min Range: -7.3067
Max Act: 6.6817. Min Act: -0.1700
Data Index: 6475588 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19