Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2548 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.5679. Min Act: -0.1700
Data Index: 2466732 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.5366. Min Act: -0.1700
Data Index: 1544585 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.5054. Min Act: -0.1700
Data Index: 1605441 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4429. Min Act: -0.1700
Data Index: 3782378 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4116. Min Act: -0.1700
Data Index: 6085528 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4116. Min Act: -0.1700
Data Index: 3324732 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.3804. Min Act: -0.1700
Data Index: 4137417 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.3804. Min Act: -0.1700
Data Index: 7020726 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.4116. Min Act: -0.1700
Data Index: 4056432 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.3491. Min Act: -0.1700
Data Index: 7235370 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.3179. Min Act: -0.1700
Data Index: 3720647 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.3491. Min Act: -0.1700
Data Index: 3024064 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.3491. Min Act: -0.1700
Data Index: 7885848 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.3491. Min Act: -0.1700
Data Index: 1331977 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.3179. Min Act: -0.1700
Data Index: 6608164 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.3179. Min Act: -0.1700
Data Index: 1933159 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.3179. Min Act: -0.1700
Data Index: 4392433 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.3179. Min Act: -0.1700
Data Index: 636425 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.3179. Min Act: -0.1700
Data Index: 6350362 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5679. Min Range: -4.5679
Max Act: 4.3179. Min Act: -0.1700
Data Index: 5952556 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19