Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 775 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.1522. Min Act: -0.1700
Data Index: 117352 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.1522. Min Act: -0.1700
Data Index: 653479 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.1522. Min Act: -0.1700
Data Index: 8705999 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.1209. Min Act: -0.1700
Data Index: 5335452 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.1209. Min Act: -0.1700
Data Index: 5529906 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.0897. Min Act: -0.1700
Data Index: 2008202 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.0897. Min Act: -0.1700
Data Index: 8265157 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.0897. Min Act: -0.1700
Data Index: 3813409 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.0584. Min Act: -0.1700
Data Index: 147415 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.0271. Min Act: -0.1700
Data Index: 134366 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.0584. Min Act: -0.1700
Data Index: 959113 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.0584. Min Act: -0.1700
Data Index: 653482 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.0271. Min Act: -0.1700
Data Index: 653485 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.0271. Min Act: -0.1700
Data Index: 3901858 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.0271. Min Act: -0.1700
Data Index: 7788889 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.0271. Min Act: -0.1700
Data Index: 3813401 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.0271. Min Act: -0.1700
Data Index: 5345584 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.0271. Min Act: -0.1700
Data Index: 1224504 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1522. Min Range: -4.1522
Max Act: 4.0271. Min Act: -0.1700
Data Index: 5284195 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1522. Min Range: -4.1522
Max Act: 3.9959. Min Act: -0.1700
Data Index: 3813416 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19