Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1858 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2671. Min Range: -7.2671
Max Act: 7.2671. Min Act: -0.1700
Data Index: 823673 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2671. Min Range: -7.2671
Max Act: 6.9546. Min Act: -0.1700
Data Index: 2132723 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2671. Min Range: -7.2671
Max Act: 6.8921. Min Act: -0.1700
Data Index: 671209 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2671. Min Range: -7.2671
Max Act: 6.8921. Min Act: -0.1700
Data Index: 1744323 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2671. Min Range: -7.2671
Max Act: 6.7358. Min Act: -0.1700
Data Index: 3352753 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2671. Min Range: -7.2671
Max Act: 6.6733. Min Act: -0.1700
Data Index: 7432800 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2671. Min Range: -7.2671
Max Act: 6.6421. Min Act: -0.1700
Data Index: 6930925 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2671. Min Range: -7.2671
Max Act: 6.6733. Min Act: -0.1700
Data Index: 7868348 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2671. Min Range: -7.2671
Max Act: 6.6733. Min Act: -0.1700
Data Index: 6562081 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2671. Min Range: -7.2671
Max Act: 6.6733. Min Act: -0.1700
Data Index: 6028204 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2671. Min Range: -7.2671
Max Act: 6.6421. Min Act: -0.1700
Data Index: 3041117 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2671. Min Range: -7.2671
Max Act: 6.5796. Min Act: -0.1700
Data Index: 2854095 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2671. Min Range: -7.2671
Max Act: 6.5796. Min Act: -0.1700
Data Index: 4485697 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2671. Min Range: -7.2671
Max Act: 6.5483. Min Act: -0.1700
Data Index: 4242200 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2671. Min Range: -7.2671
Max Act: 6.5171. Min Act: -0.1700
Data Index: 5003262 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2671. Min Range: -7.2671
Max Act: 6.5171. Min Act: -0.1700
Data Index: 2271913 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2671. Min Range: -7.2671
Max Act: 6.4858. Min Act: -0.1700
Data Index: 223652 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2671. Min Range: -7.2671
Max Act: 6.5171. Min Act: -0.1700
Data Index: 4035187 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2671. Min Range: -7.2671
Max Act: 6.4546. Min Act: -0.1700
Data Index: 3582311 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2671. Min Range: -7.2671
Max Act: 6.4546. Min Act: -0.1700
Data Index: 441988 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19