Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3025 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0096. Min Range: -5.0096
Max Act: 5.0096. Min Act: -0.1700
Data Index: 7659724 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0096. Min Range: -5.0096
Max Act: 4.6034. Min Act: -0.1700
Data Index: 7684580 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0096. Min Range: -5.0096
Max Act: 4.5721. Min Act: -0.1700
Data Index: 1237098 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0096. Min Range: -5.0096
Max Act: 4.6034. Min Act: -0.1700
Data Index: 8183454 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0096. Min Range: -5.0096
Max Act: 4.5721. Min Act: -0.1700
Data Index: 7885295 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0096. Min Range: -5.0096
Max Act: 4.5409. Min Act: -0.1700
Data Index: 3063629 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0096. Min Range: -5.0096
Max Act: 4.5721. Min Act: -0.1700
Data Index: 471856 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0096. Min Range: -5.0096
Max Act: 4.5096. Min Act: -0.1700
Data Index: 735489 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0096. Min Range: -5.0096
Max Act: 4.5096. Min Act: -0.1700
Data Index: 3951596 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0096. Min Range: -5.0096
Max Act: 4.4471. Min Act: -0.1700
Data Index: 5537852 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0096. Min Range: -5.0096
Max Act: 4.4159. Min Act: -0.1700
Data Index: 4783352 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0096. Min Range: -5.0096
Max Act: 4.4471. Min Act: -0.1700
Data Index: 4298703 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0096. Min Range: -5.0096
Max Act: 4.4159. Min Act: -0.1700
Data Index: 2609234 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0096. Min Range: -5.0096
Max Act: 4.4159. Min Act: -0.1700
Data Index: 1645294 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0096. Min Range: -5.0096
Max Act: 4.4159. Min Act: -0.1700
Data Index: 1093116 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0096. Min Range: -5.0096
Max Act: 4.3846. Min Act: -0.1700
Data Index: 1107098 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0096. Min Range: -5.0096
Max Act: 4.3846. Min Act: -0.1700
Data Index: 4113867 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0096. Min Range: -5.0096
Max Act: 4.3846. Min Act: -0.1700
Data Index: 2078605 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0096. Min Range: -5.0096
Max Act: 4.3534. Min Act: -0.1700
Data Index: 6847303 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0096. Min Range: -5.0096
Max Act: 4.3846. Min Act: -0.1700
Data Index: 5951157 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19