Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1840 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.6323. Min Act: -0.1700
Data Index: 7125691 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.4448. Min Act: -0.1700
Data Index: 1205929 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.4448. Min Act: -0.1700
Data Index: 6288597 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.3510. Min Act: -0.1700
Data Index: 5263699 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.3198. Min Act: -0.1700
Data Index: 5487574 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.2885. Min Act: -0.1700
Data Index: 7024886 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.2573. Min Act: -0.1700
Data Index: 3461403 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.2260. Min Act: -0.1700
Data Index: 6266241 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.2260. Min Act: -0.1700
Data Index: 3081094 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.1948. Min Act: -0.1700
Data Index: 5841901 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.1948. Min Act: -0.1700
Data Index: 5523046 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.1948. Min Act: -0.1700
Data Index: 7165562 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.1948. Min Act: -0.1700
Data Index: 1833306 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.1948. Min Act: -0.1700
Data Index: 81285 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.1948. Min Act: -0.1700
Data Index: 988909 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.1635. Min Act: -0.1700
Data Index: 8638662 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.1323. Min Act: -0.1700
Data Index: 4511949 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.1323. Min Act: -0.1700
Data Index: 7509930 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.1635. Min Act: -0.1700
Data Index: 8011125 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.1323. Min Act: -0.1700
Data Index: 8054355 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19