Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4430 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.8234. Min Act: -0.1700
Data Index: 858031 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.7921. Min Act: -0.1700
Data Index: 2723280 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.7296. Min Act: -0.1700
Data Index: 1052727 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.7296. Min Act: -0.1700
Data Index: 2838344 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.6359. Min Act: -0.1700
Data Index: 1603167 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.6671. Min Act: -0.1700
Data Index: 7400991 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.6359. Min Act: -0.1700
Data Index: 286608 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.6359. Min Act: -0.1700
Data Index: 1170167 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.6359. Min Act: -0.1700
Data Index: 6896539 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.6046. Min Act: -0.1700
Data Index: 5799016 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.5734. Min Act: -0.1700
Data Index: 2027109 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.5734. Min Act: -0.1700
Data Index: 238711 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.5421. Min Act: -0.1700
Data Index: 2986425 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.5421. Min Act: -0.1700
Data Index: 6949777 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.5421. Min Act: -0.1700
Data Index: 4785962 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.5109. Min Act: -0.1700
Data Index: 2001183 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.5421. Min Act: -0.1700
Data Index: 1871960 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.5109. Min Act: -0.1700
Data Index: 549382 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.4484. Min Act: -0.1700
Data Index: 5462397 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8234. Min Range: -5.8234
Max Act: 5.4484. Min Act: -0.1700
Data Index: 5740392 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19