Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1656 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2753. Min Range: -4.2753
Max Act: 4.2753. Min Act: -0.1700
Data Index: 7083550 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2753. Min Range: -4.2753
Max Act: 4.1503. Min Act: -0.1700
Data Index: 8042190 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2753. Min Range: -4.2753
Max Act: 4.0877. Min Act: -0.1700
Data Index: 604219 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2753. Min Range: -4.2753
Max Act: 4.0877. Min Act: -0.1700
Data Index: 2534525 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2753. Min Range: -4.2753
Max Act: 4.0565. Min Act: -0.1700
Data Index: 2844022 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2753. Min Range: -4.2753
Max Act: 4.0096. Min Act: -0.1700
Data Index: 7228356 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2753. Min Range: -4.2753
Max Act: 4.0252. Min Act: -0.1700
Data Index: 5973692 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2753. Min Range: -4.2753
Max Act: 3.9627. Min Act: -0.1700
Data Index: 5059195 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2753. Min Range: -4.2753
Max Act: 3.9471. Min Act: -0.1700
Data Index: 7372420 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2753. Min Range: -4.2753
Max Act: 3.9627. Min Act: -0.1700
Data Index: 7816838 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2753. Min Range: -4.2753
Max Act: 3.9627. Min Act: -0.1700
Data Index: 5094568 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2753. Min Range: -4.2753
Max Act: 3.9783. Min Act: -0.1700
Data Index: 5652284 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2753. Min Range: -4.2753
Max Act: 3.9471. Min Act: -0.1700
Data Index: 6701174 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2753. Min Range: -4.2753
Max Act: 3.9471. Min Act: -0.1700
Data Index: 4724629 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2753. Min Range: -4.2753
Max Act: 3.9158. Min Act: -0.1700
Data Index: 8188548 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2753. Min Range: -4.2753
Max Act: 3.9158. Min Act: -0.1700
Data Index: 7198532 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2753. Min Range: -4.2753
Max Act: 3.9002. Min Act: -0.1700
Data Index: 2445295 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2753. Min Range: -4.2753
Max Act: 3.9002. Min Act: -0.1700
Data Index: 401458 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2753. Min Range: -4.2753
Max Act: 3.8689. Min Act: -0.1700
Data Index: 1118650 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2753. Min Range: -4.2753
Max Act: 3.8845. Min Act: -0.1700
Data Index: 2598421 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19