Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2804 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0777. Min Range: -3.0777
Max Act: 3.0777. Min Act: -0.1700
Data Index: 4178332 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0777. Min Range: -3.0777
Max Act: 3.0461. Min Act: -0.1700
Data Index: 4831859 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0777. Min Range: -3.0777
Max Act: 3.0461. Min Act: -0.1700
Data Index: 8260728 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0777. Min Range: -3.0777
Max Act: 3.0461. Min Act: -0.1700
Data Index: 7426063 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0777. Min Range: -3.0777
Max Act: 3.0145. Min Act: -0.1700
Data Index: 7099519 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0777. Min Range: -3.0777
Max Act: 3.0145. Min Act: -0.1700
Data Index: 3576635 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0777. Min Range: -3.0777
Max Act: 2.9987. Min Act: -0.1700
Data Index: 6632991 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0777. Min Range: -3.0777
Max Act: 3.0145. Min Act: -0.1700
Data Index: 6268794 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0777. Min Range: -3.0777
Max Act: 3.0145. Min Act: -0.1700
Data Index: 1642466 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0777. Min Range: -3.0777
Max Act: 2.9829. Min Act: -0.1700
Data Index: 823591 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0777. Min Range: -3.0777
Max Act: 2.9829. Min Act: -0.1700
Data Index: 6517378 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0777. Min Range: -3.0777
Max Act: 2.9671. Min Act: -0.1700
Data Index: 7939089 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0777. Min Range: -3.0777
Max Act: 2.9829. Min Act: -0.1700
Data Index: 386445 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0777. Min Range: -3.0777
Max Act: 2.9829. Min Act: -0.1700
Data Index: 444892 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0777. Min Range: -3.0777
Max Act: 2.9829. Min Act: -0.1700
Data Index: 5017650 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0777. Min Range: -3.0777
Max Act: 2.9987. Min Act: -0.1700
Data Index: 4067673 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0777. Min Range: -3.0777
Max Act: 2.9829. Min Act: -0.1700
Data Index: 6223912 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0777. Min Range: -3.0777
Max Act: 2.9829. Min Act: -0.1700
Data Index: 2094512 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0777. Min Range: -3.0777
Max Act: 2.9671. Min Act: -0.1700
Data Index: 3576636 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0777. Min Range: -3.0777
Max Act: 2.9671. Min Act: -0.1700
Data Index: 1738051 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19