Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 989 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.8579. Min Act: -0.1700
Data Index: 4797160 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.8423. Min Act: -0.1700
Data Index: 2000872 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.8267. Min Act: -0.1700
Data Index: 8037449 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.7954. Min Act: -0.1700
Data Index: 5581887 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.7641. Min Act: -0.1700
Data Index: 305199 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.7485. Min Act: -0.1700
Data Index: 619276 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.7641. Min Act: -0.1700
Data Index: 7315080 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.7797. Min Act: -0.1700
Data Index: 6530650 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.7485. Min Act: -0.1700
Data Index: 4538420 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.7328. Min Act: -0.1700
Data Index: 7509328 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.7485. Min Act: -0.1700
Data Index: 5512008 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.7172. Min Act: -0.1700
Data Index: 6925785 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.7172. Min Act: -0.1700
Data Index: 4107764 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.7015. Min Act: -0.1700
Data Index: 8025373 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.7015. Min Act: -0.1700
Data Index: 8382086 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.7015. Min Act: -0.1700
Data Index: 8541442 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.7015. Min Act: -0.1700
Data Index: 8032142 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.6703. Min Act: -0.1700
Data Index: 4741037 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.6703. Min Act: -0.1700
Data Index: 7557277 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8579. Min Range: -3.8579
Max Act: 3.6703. Min Act: -0.1700
Data Index: 7859804 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19