Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1135 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.2822. Min Act: -0.1700
Data Index: 868219 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.2979. Min Act: -0.1700
Data Index: 1834660 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.2508. Min Act: -0.1700
Data Index: 7555040 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.2508. Min Act: -0.1700
Data Index: 4666022 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.2351. Min Act: -0.1700
Data Index: 6133916 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.2037. Min Act: -0.1700
Data Index: 6225523 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.2351. Min Act: -0.1700
Data Index: 8644233 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.2351. Min Act: -0.1700
Data Index: 3879384 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.2351. Min Act: -0.1700
Data Index: 3132358 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.1879. Min Act: -0.1700
Data Index: 3533536 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.1722. Min Act: -0.1700
Data Index: 3549909 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.1407. Min Act: -0.1700
Data Index: 3069127 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.1565. Min Act: -0.1700
Data Index: 4135695 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.1722. Min Act: -0.1700
Data Index: 2654560 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.1407. Min Act: -0.1700
Data Index: 6163157 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.1407. Min Act: -0.1700
Data Index: 5622077 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.1092. Min Act: -0.1700
Data Index: 910257 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.1250. Min Act: -0.1700
Data Index: 7691156 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.1250. Min Act: -0.1700
Data Index: 7152753 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2979. Min Range: -3.2979
Max Act: 3.0935. Min Act: -0.1700
Data Index: 3707979 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19