Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2903 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0492. Min Range: -4.0492
Max Act: 4.0492. Min Act: -0.1700
Data Index: 8343097 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0492. Min Range: -4.0492
Max Act: 4.0180. Min Act: -0.1700
Data Index: 2704477 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0492. Min Range: -4.0492
Max Act: 4.0180. Min Act: -0.1700
Data Index: 1604472 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.9398. Min Act: -0.1700
Data Index: 27437 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.9554. Min Act: -0.1700
Data Index: 5066191 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.9398. Min Act: -0.1700
Data Index: 333220 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.9242. Min Act: -0.1700
Data Index: 306471 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.9398. Min Act: -0.1700
Data Index: 1194259 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.8929. Min Act: -0.1700
Data Index: 5515184 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.8616. Min Act: -0.1700
Data Index: 578792 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.8616. Min Act: -0.1700
Data Index: 8626022 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.8460. Min Act: -0.1700
Data Index: 8609034 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.8616. Min Act: -0.1700
Data Index: 5864869 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.8460. Min Act: -0.1700
Data Index: 6457590 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.8460. Min Act: -0.1700
Data Index: 1864309 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.7991. Min Act: -0.1700
Data Index: 315130 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.7991. Min Act: -0.1700
Data Index: 3773729 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.8304. Min Act: -0.1700
Data Index: 1605418 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.7835. Min Act: -0.1700
Data Index: 7834911 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0492. Min Range: -4.0492
Max Act: 3.7835. Min Act: -0.1700
Data Index: 305504 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19