Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3219 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4281. Min Range: -8.4281
Max Act: 8.4281. Min Act: -0.1700
Data Index: 5921252 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4281. Min Range: -8.4281
Max Act: 8.3656. Min Act: -0.1700
Data Index: 2942995 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4281. Min Range: -8.4281
Max Act: 8.2406. Min Act: -0.1700
Data Index: 2246919 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4281. Min Range: -8.4281
Max Act: 8.2094. Min Act: -0.1700
Data Index: 4582088 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4281. Min Range: -8.4281
Max Act: 8.1469. Min Act: -0.1700
Data Index: 4844661 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4281. Min Range: -8.4281
Max Act: 8.1469. Min Act: -0.1700
Data Index: 6058403 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4281. Min Range: -8.4281
Max Act: 8.1469. Min Act: -0.1700
Data Index: 8381902 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4281. Min Range: -8.4281
Max Act: 8.1469. Min Act: -0.1700
Data Index: 7853907 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4281. Min Range: -8.4281
Max Act: 8.0844. Min Act: -0.1697
Data Index: 5130285 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4281. Min Range: -8.4281
Max Act: 8.0531. Min Act: -0.1700
Data Index: 6651249 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4281. Min Range: -8.4281
Max Act: 8.0531. Min Act: -0.1700
Data Index: 5993183 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4281. Min Range: -8.4281
Max Act: 8.0531. Min Act: -0.1700
Data Index: 5414879 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4281. Min Range: -8.4281
Max Act: 8.0219. Min Act: -0.1700
Data Index: 5817024 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4281. Min Range: -8.4281
Max Act: 7.9906. Min Act: -0.1700
Data Index: 2722545 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4281. Min Range: -8.4281
Max Act: 7.9906. Min Act: -0.1700
Data Index: 5631750 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4281. Min Range: -8.4281
Max Act: 7.9594. Min Act: -0.1700
Data Index: 7314028 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4281. Min Range: -8.4281
Max Act: 7.9594. Min Act: -0.1700
Data Index: 2284038 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4281. Min Range: -8.4281
Max Act: 7.9594. Min Act: -0.1700
Data Index: 6108617 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4281. Min Range: -8.4281
Max Act: 7.9281. Min Act: -0.1696
Data Index: 797965 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4281. Min Range: -8.4281
Max Act: 7.9281. Min Act: -0.1700
Data Index: 6456038 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19