Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3089 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.6412. Min Act: -0.1700
Data Index: 478119 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.5787. Min Act: -0.1700
Data Index: 5440548 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.5162. Min Act: -0.1700
Data Index: 1705680 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.5162. Min Act: -0.1700
Data Index: 5392805 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.4850. Min Act: -0.1700
Data Index: 3502018 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.4850. Min Act: -0.1700
Data Index: 4833969 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.4537. Min Act: -0.1700
Data Index: 8642334 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.4225. Min Act: -0.1700
Data Index: 5727790 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.3912. Min Act: -0.1700
Data Index: 3547930 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.3599. Min Act: -0.1700
Data Index: 418699 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.3599. Min Act: -0.1700
Data Index: 2599442 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.3287. Min Act: -0.1700
Data Index: 3306810 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.3287. Min Act: -0.1700
Data Index: 8367940 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.3287. Min Act: -0.1700
Data Index: 8812904 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.2974. Min Act: -0.1700
Data Index: 5046521 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.2974. Min Act: -0.1700
Data Index: 5713481 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.2974. Min Act: -0.1700
Data Index: 6912816 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.2974. Min Act: -0.1700
Data Index: 6212976 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.2974. Min Act: -0.1700
Data Index: 426937 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6412. Min Range: -4.6412
Max Act: 4.2974. Min Act: -0.1700
Data Index: 4809986 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19