Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3544 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0314. Min Range: -4.0314
Max Act: 4.0314. Min Act: -0.1700
Data Index: 6994664 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0314. Min Range: -4.0314
Max Act: 4.0001. Min Act: -0.1700
Data Index: 5125989 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0314. Min Range: -4.0314
Max Act: 3.9689. Min Act: -0.1700
Data Index: 358923 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0314. Min Range: -4.0314
Max Act: 3.9689. Min Act: -0.1700
Data Index: 3299419 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0314. Min Range: -4.0314
Max Act: 3.8594. Min Act: -0.1700
Data Index: 3863630 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0314. Min Range: -4.0314
Max Act: 3.8751. Min Act: -0.1700
Data Index: 3049094 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0314. Min Range: -4.0314
Max Act: 3.8594. Min Act: -0.1700
Data Index: 3925915 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0314. Min Range: -4.0314
Max Act: 3.8751. Min Act: -0.1700
Data Index: 6571376 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0314. Min Range: -4.0314
Max Act: 3.8594. Min Act: -0.1700
Data Index: 7360613 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0314. Min Range: -4.0314
Max Act: 3.8125. Min Act: -0.1700
Data Index: 4257214 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0314. Min Range: -4.0314
Max Act: 3.7500. Min Act: -0.1700
Data Index: 3521982 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0314. Min Range: -4.0314
Max Act: 3.7656. Min Act: -0.1700
Data Index: 3783528 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0314. Min Range: -4.0314
Max Act: 3.7656. Min Act: -0.1700
Data Index: 2660157 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0314. Min Range: -4.0314
Max Act: 3.7343. Min Act: -0.1700
Data Index: 2364292 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0314. Min Range: -4.0314
Max Act: 3.7500. Min Act: -0.1700
Data Index: 7609148 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0314. Min Range: -4.0314
Max Act: 3.7343. Min Act: -0.1700
Data Index: 7896851 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0314. Min Range: -4.0314
Max Act: 3.7343. Min Act: -0.1700
Data Index: 5050842 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0314. Min Range: -4.0314
Max Act: 3.7187. Min Act: -0.1700
Data Index: 2972510 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0314. Min Range: -4.0314
Max Act: 3.7187. Min Act: -0.1700
Data Index: 810366 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0314. Min Range: -4.0314
Max Act: 3.7187. Min Act: -0.1700
Data Index: 3760666 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19