Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5397 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.6395. Min Act: -0.1700
Data Index: 2101609 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.4833. Min Act: -0.1700
Data Index: 2186468 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.4208. Min Act: -0.1700
Data Index: 3365311 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.4208. Min Act: -0.1700
Data Index: 4139959 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.4208. Min Act: -0.1700
Data Index: 5496582 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.3895. Min Act: -0.1700
Data Index: 980415 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.3270. Min Act: -0.1700
Data Index: 7004752 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.3270. Min Act: -0.1700
Data Index: 356844 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.2958. Min Act: -0.1700
Data Index: 8103478 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.2333. Min Act: -0.1700
Data Index: 8447865 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.2333. Min Act: -0.1700
Data Index: 7095029 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.2020. Min Act: -0.1700
Data Index: 1432276 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.2020. Min Act: -0.1700
Data Index: 6125054 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.1708. Min Act: -0.1700
Data Index: 7701259 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.2020. Min Act: -0.1700
Data Index: 6086933 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.1708. Min Act: -0.1700
Data Index: 7139279 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.1083. Min Act: -0.1700
Data Index: 5227468 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.1083. Min Act: -0.1700
Data Index: 963147 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.0770. Min Act: -0.1700
Data Index: 6663806 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6395. Min Range: -6.6395
Max Act: 6.0770. Min Act: -0.1700
Data Index: 6374895 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19