Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3594 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0306. Min Range: -5.0306
Max Act: 5.0306. Min Act: -0.1700
Data Index: 3420895 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0306. Min Range: -5.0306
Max Act: 4.9056. Min Act: -0.1700
Data Index: 3420894 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0306. Min Range: -5.0306
Max Act: 4.9368. Min Act: -0.1700
Data Index: 3878477 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0306. Min Range: -5.0306
Max Act: 4.9368. Min Act: -0.1700
Data Index: 3863596 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0306. Min Range: -5.0306
Max Act: 4.8743. Min Act: -0.1700
Data Index: 6331123 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0306. Min Range: -5.0306
Max Act: 4.9056. Min Act: -0.1700
Data Index: 3286092 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0306. Min Range: -5.0306
Max Act: 4.9056. Min Act: -0.1700
Data Index: 5224694 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0306. Min Range: -5.0306
Max Act: 4.8743. Min Act: -0.1700
Data Index: 7412308 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0306. Min Range: -5.0306
Max Act: 4.8743. Min Act: -0.1700
Data Index: 259727 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0306. Min Range: -5.0306
Max Act: 4.9056. Min Act: -0.1700
Data Index: 4707331 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0306. Min Range: -5.0306
Max Act: 4.9056. Min Act: -0.1700
Data Index: 102168 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0306. Min Range: -5.0306
Max Act: 4.8743. Min Act: -0.1700
Data Index: 8664111 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0306. Min Range: -5.0306
Max Act: 4.8743. Min Act: -0.1700
Data Index: 4175141 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0306. Min Range: -5.0306
Max Act: 4.8743. Min Act: -0.1700
Data Index: 1419033 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0306. Min Range: -5.0306
Max Act: 4.8431. Min Act: -0.1700
Data Index: 5243917 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0306. Min Range: -5.0306
Max Act: 4.8431. Min Act: -0.1700
Data Index: 6287922 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0306. Min Range: -5.0306
Max Act: 4.8118. Min Act: -0.1700
Data Index: 1167134 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0306. Min Range: -5.0306
Max Act: 4.8431. Min Act: -0.1700
Data Index: 7159817 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0306. Min Range: -5.0306
Max Act: 4.8431. Min Act: -0.1700
Data Index: 831367 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0306. Min Range: -5.0306
Max Act: 4.8118. Min Act: -0.1700
Data Index: 5035550 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19