Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 983 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.9232. Min Act: -0.1700
Data Index: 1276085 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.9232. Min Act: -0.1700
Data Index: 2158480 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.6732. Min Act: -0.1700
Data Index: 6945691 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.6419. Min Act: -0.1700
Data Index: 1935169 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.6419. Min Act: -0.1700
Data Index: 3263759 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.6419. Min Act: -0.1700
Data Index: 7237432 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.6107. Min Act: -0.1700
Data Index: 1321389 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.5794. Min Act: -0.1700
Data Index: 5567778 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.5794. Min Act: -0.1700
Data Index: 1403855 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.6107. Min Act: -0.1700
Data Index: 7534376 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.4857. Min Act: -0.1700
Data Index: 6601578 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.5169. Min Act: -0.1700
Data Index: 3672600 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.4857. Min Act: -0.1700
Data Index: 2660679 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.4857. Min Act: -0.1700
Data Index: 7703280 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.4857. Min Act: -0.1700
Data Index: 7727013 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.4857. Min Act: -0.1700
Data Index: 1334348 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.5169. Min Act: -0.1700
Data Index: 4866541 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.4857. Min Act: -0.1700
Data Index: 6256772 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.4544. Min Act: -0.1700
Data Index: 5710669 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9232. Min Range: -7.9232
Max Act: 7.4232. Min Act: -0.1700
Data Index: 1947081 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19