Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3038 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5422. Min Range: -4.5422
Max Act: 4.5422. Min Act: -0.1700
Data Index: 4184985 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5422. Min Range: -4.5422
Max Act: 3.8546. Min Act: -0.1700
Data Index: 5304400 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5422. Min Range: -4.5422
Max Act: 3.8546. Min Act: -0.1700
Data Index: 3242626 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5422. Min Range: -4.5422
Max Act: 3.7920. Min Act: -0.1700
Data Index: 6374652 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5422. Min Range: -4.5422
Max Act: 3.7920. Min Act: -0.1700
Data Index: 2599352 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5422. Min Range: -4.5422
Max Act: 3.7920. Min Act: -0.1700
Data Index: 4023708 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5422. Min Range: -4.5422
Max Act: 3.7764. Min Act: -0.1700
Data Index: 4047631 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5422. Min Range: -4.5422
Max Act: 3.7607. Min Act: -0.1700
Data Index: 478486 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5422. Min Range: -4.5422
Max Act: 3.7607. Min Act: -0.1700
Data Index: 1170626 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5422. Min Range: -4.5422
Max Act: 3.7451. Min Act: -0.1700
Data Index: 5734161 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5422. Min Range: -4.5422
Max Act: 3.7295. Min Act: -0.1700
Data Index: 3101234 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5422. Min Range: -4.5422
Max Act: 3.7295. Min Act: -0.1700
Data Index: 6913614 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5422. Min Range: -4.5422
Max Act: 3.7295. Min Act: -0.1700
Data Index: 778862 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5422. Min Range: -4.5422
Max Act: 3.7295. Min Act: -0.1700
Data Index: 962960 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5422. Min Range: -4.5422
Max Act: 3.6982. Min Act: -0.1700
Data Index: 4949659 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5422. Min Range: -4.5422
Max Act: 3.6982. Min Act: -0.1700
Data Index: 576429 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5422. Min Range: -4.5422
Max Act: 3.6982. Min Act: -0.1700
Data Index: 8155736 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5422. Min Range: -4.5422
Max Act: 3.7138. Min Act: -0.1700
Data Index: 4629132 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5422. Min Range: -4.5422
Max Act: 3.6825. Min Act: -0.1700
Data Index: 8655612 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5422. Min Range: -4.5422
Max Act: 3.6982. Min Act: -0.1700
Data Index: 2184963 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19