Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2398 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0638. Min Range: -9.0638
Max Act: 9.0638. Min Act: -0.1700
Data Index: 4440972 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0638. Min Range: -9.0638
Max Act: 8.7513. Min Act: -0.1700
Data Index: 464685 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0638. Min Range: -9.0638
Max Act: 8.7513. Min Act: -0.1700
Data Index: 378751 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0638. Min Range: -9.0638
Max Act: 8.6888. Min Act: -0.1700
Data Index: 4231382 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0638. Min Range: -9.0638
Max Act: 8.6263. Min Act: -0.1700
Data Index: 1670835 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0638. Min Range: -9.0638
Max Act: 8.5638. Min Act: -0.1700
Data Index: 7686293 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0638. Min Range: -9.0638
Max Act: 8.5013. Min Act: -0.1700
Data Index: 1670839 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0638. Min Range: -9.0638
Max Act: 8.4388. Min Act: -0.1700
Data Index: 7419614 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0638. Min Range: -9.0638
Max Act: 8.5013. Min Act: -0.1700
Data Index: 601109 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0638. Min Range: -9.0638
Max Act: 8.4388. Min Act: -0.1700
Data Index: 2882358 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0638. Min Range: -9.0638
Max Act: 8.3763. Min Act: -0.1700
Data Index: 3186105 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0638. Min Range: -9.0638
Max Act: 8.3763. Min Act: -0.1700
Data Index: 6648482 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0638. Min Range: -9.0638
Max Act: 8.3763. Min Act: -0.1700
Data Index: 275608 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0638. Min Range: -9.0638
Max Act: 8.4388. Min Act: -0.1700
Data Index: 5794994 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0638. Min Range: -9.0638
Max Act: 8.3138. Min Act: -0.1700
Data Index: 3416383 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0638. Min Range: -9.0638
Max Act: 8.3138. Min Act: -0.1700
Data Index: 7839428 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0638. Min Range: -9.0638
Max Act: 8.3138. Min Act: -0.1700
Data Index: 2934630 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0638. Min Range: -9.0638
Max Act: 8.2513. Min Act: -0.1700
Data Index: 7694158 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0638. Min Range: -9.0638
Max Act: 8.2200. Min Act: -0.1700
Data Index: 2628418 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0638. Min Range: -9.0638
Max Act: 8.2513. Min Act: -0.1700
Data Index: 7484173 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19