Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2134 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.9592. Min Act: -0.1700
Data Index: 1862561 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.8342. Min Act: -0.1700
Data Index: 451696 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.8655. Min Act: -0.1700
Data Index: 2669501 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.7717. Min Act: -0.1700
Data Index: 8304653 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.7092. Min Act: -0.1700
Data Index: 6861366 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.6155. Min Act: -0.1700
Data Index: 7399624 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.5530. Min Act: -0.1700
Data Index: 1358057 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.5217. Min Act: -0.1700
Data Index: 6883270 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.5217. Min Act: -0.1700
Data Index: 3872341 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.4905. Min Act: -0.1700
Data Index: 5970682 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.4592. Min Act: -0.1700
Data Index: 3595377 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.4280. Min Act: -0.1700
Data Index: 407578 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.4905. Min Act: -0.1700
Data Index: 4468822 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.4592. Min Act: -0.1700
Data Index: 5221799 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.4280. Min Act: -0.1700
Data Index: 816586 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.4280. Min Act: -0.1700
Data Index: 6887027 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.3967. Min Act: -0.1700
Data Index: 3044500 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.3655. Min Act: -0.1700
Data Index: 6802198 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.3342. Min Act: -0.1700
Data Index: 5684154 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9592. Min Range: -6.9592
Max Act: 6.3655. Min Act: -0.1700
Data Index: 4884500 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19