Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3722 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.5537. Min Act: -0.1700
Data Index: 4738658 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.5224. Min Act: -0.1700
Data Index: 3189089 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.4911. Min Act: -0.1700
Data Index: 3995355 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.4754. Min Act: -0.1700
Data Index: 406459 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.4754. Min Act: -0.1700
Data Index: 735768 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.4754. Min Act: -0.1700
Data Index: 2091306 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.4754. Min Act: -0.1700
Data Index: 6362219 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.4597. Min Act: -0.1700
Data Index: 2365525 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.4597. Min Act: -0.1700
Data Index: 7314391 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.4754. Min Act: -0.1700
Data Index: 480747 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.4597. Min Act: -0.1700
Data Index: 5406657 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.4441. Min Act: -0.1700
Data Index: 4538320 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.4284. Min Act: -0.1700
Data Index: 3899006 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.4441. Min Act: -0.1700
Data Index: 2644707 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.4284. Min Act: -0.1700
Data Index: 3213077 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.4127. Min Act: -0.1700
Data Index: 4390959 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.4284. Min Act: -0.1700
Data Index: 3416928 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.4127. Min Act: -0.1700
Data Index: 2131592 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.4127. Min Act: -0.1700
Data Index: 6238783 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5537. Min Range: -3.5537
Max Act: 3.3971. Min Act: -0.1700
Data Index: 7261071 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19