Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3623 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.9592. Min Act: -0.1700
Data Index: 3706829 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.8967. Min Act: -0.1700
Data Index: 633422 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.8342. Min Act: -0.1700
Data Index: 2044056 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.7717. Min Act: -0.1700
Data Index: 1059573 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.7717. Min Act: -0.1700
Data Index: 6460100 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.7717. Min Act: -0.1700
Data Index: 710324 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.7092. Min Act: -0.1700
Data Index: 5861755 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.6467. Min Act: -0.1700
Data Index: 8678951 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.5842. Min Act: -0.1700
Data Index: 6873119 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.5842. Min Act: -0.1700
Data Index: 1688457 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.5842. Min Act: -0.1700
Data Index: 5439505 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.5217. Min Act: -0.1700
Data Index: 3400935 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.4592. Min Act: -0.1700
Data Index: 5742271 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.4592. Min Act: -0.1700
Data Index: 2441861 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.4592. Min Act: -0.1700
Data Index: 6740495 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.5217. Min Act: -0.1700
Data Index: 300824 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.3967. Min Act: -0.1700
Data Index: 1808816 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.3967. Min Act: -0.1700
Data Index: 6442575 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.3342. Min Act: -0.1700
Data Index: 2416165 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9592. Min Range: -11.9592
Max Act: 11.3342. Min Act: -0.1700
Data Index: 648619 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19