Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3822 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1870. Min Range: -5.1870
Max Act: 5.1870. Min Act: -0.1700
Data Index: 929662 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1870. Min Range: -5.1870
Max Act: 5.1870. Min Act: -0.1700
Data Index: 6449622 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1870. Min Range: -5.1870
Max Act: 5.0307. Min Act: -0.1700
Data Index: 1528452 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1870. Min Range: -5.1870
Max Act: 4.8745. Min Act: -0.1700
Data Index: 1323355 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1870. Min Range: -5.1870
Max Act: 4.8432. Min Act: -0.1700
Data Index: 4071585 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1870. Min Range: -5.1870
Max Act: 4.8432. Min Act: -0.1700
Data Index: 6627241 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1870. Min Range: -5.1870
Max Act: 4.8120. Min Act: -0.1700
Data Index: 5336182 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1870. Min Range: -5.1870
Max Act: 4.7807. Min Act: -0.1700
Data Index: 4468021 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1870. Min Range: -5.1870
Max Act: 4.7182. Min Act: -0.1700
Data Index: 6415637 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1870. Min Range: -5.1870
Max Act: 4.7495. Min Act: -0.1700
Data Index: 3066428 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1870. Min Range: -5.1870
Max Act: 4.7182. Min Act: -0.1700
Data Index: 977243 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1870. Min Range: -5.1870
Max Act: 4.7182. Min Act: -0.1700
Data Index: 7390602 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1870. Min Range: -5.1870
Max Act: 4.6557. Min Act: -0.1700
Data Index: 6853070 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1870. Min Range: -5.1870
Max Act: 4.6557. Min Act: -0.1700
Data Index: 3449557 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1870. Min Range: -5.1870
Max Act: 4.5932. Min Act: -0.1700
Data Index: 52067 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1870. Min Range: -5.1870
Max Act: 4.6245. Min Act: -0.1700
Data Index: 1179155 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1870. Min Range: -5.1870
Max Act: 4.5620. Min Act: -0.1700
Data Index: 6763205 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1870. Min Range: -5.1870
Max Act: 4.5932. Min Act: -0.1700
Data Index: 1153511 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1870. Min Range: -5.1870
Max Act: 4.5307. Min Act: -0.1700
Data Index: 5616520 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1870. Min Range: -5.1870
Max Act: 4.5932. Min Act: -0.1700
Data Index: 67095 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19