Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.9602. Min Act: -0.1700
Data Index: 2979457 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.8977. Min Act: -0.1700
Data Index: 4189027 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.7415. Min Act: -0.1700
Data Index: 279972 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.7727. Min Act: -0.1700
Data Index: 5824166 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.7415. Min Act: -0.1700
Data Index: 6870326 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.7102. Min Act: -0.1700
Data Index: 8324081 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.7415. Min Act: -0.1700
Data Index: 5884248 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.6790. Min Act: -0.1700
Data Index: 2702888 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.7102. Min Act: -0.1700
Data Index: 6189801 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.6165. Min Act: -0.1700
Data Index: 2761136 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.6165. Min Act: -0.1700
Data Index: 3573037 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.5852. Min Act: -0.1700
Data Index: 4879644 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.6165. Min Act: -0.1700
Data Index: 4002305 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.5540. Min Act: -0.1700
Data Index: 5094416 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.5540. Min Act: -0.1700
Data Index: 7500033 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.5227. Min Act: -0.1700
Data Index: 6165672 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.5540. Min Act: -0.1700
Data Index: 5114420 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.5227. Min Act: -0.1700
Data Index: 7220720 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.5227. Min Act: -0.1700
Data Index: 1947667 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9602. Min Range: -4.9602
Max Act: 4.4602. Min Act: -0.1700
Data Index: 2027089 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19