Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3810 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.7222. Min Act: -0.1700
Data Index: 366563 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.7222. Min Act: -0.1700
Data Index: 3315082 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.7534. Min Act: -0.1700
Data Index: 8156522 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.7222. Min Act: -0.1700
Data Index: 1277326 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.7222. Min Act: -0.1700
Data Index: 647628 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.7222. Min Act: -0.1700
Data Index: 6444620 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.6909. Min Act: -0.1700
Data Index: 505611 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.6909. Min Act: -0.1700
Data Index: 416235 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.6597. Min Act: -0.1700
Data Index: 2519052 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.6597. Min Act: -0.1700
Data Index: 2490129 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.6597. Min Act: -0.1700
Data Index: 6501372 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.6597. Min Act: -0.1700
Data Index: 8711348 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.6909. Min Act: -0.1700
Data Index: 3970432 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.6284. Min Act: -0.1700
Data Index: 4554348 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.6284. Min Act: -0.1700
Data Index: 5424553 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.6284. Min Act: -0.1700
Data Index: 5207546 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.6284. Min Act: -0.1700
Data Index: 7397282 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.6284. Min Act: -0.1700
Data Index: 7595400 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.6284. Min Act: -0.1700
Data Index: 2337454 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7534. Min Range: -4.7534
Max Act: 4.5972. Min Act: -0.1700
Data Index: 7220959 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19