Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3844 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1792. Min Range: -5.1792
Max Act: 5.1792. Min Act: -0.1700
Data Index: 4855628 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1792. Min Range: -5.1792
Max Act: 4.8355. Min Act: -0.1700
Data Index: 1482185 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1792. Min Range: -5.1792
Max Act: 4.8355. Min Act: -0.1700
Data Index: 1888458 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1792. Min Range: -5.1792
Max Act: 4.7730. Min Act: -0.1700
Data Index: 2708991 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1792. Min Range: -5.1792
Max Act: 4.7417. Min Act: -0.1700
Data Index: 2709001 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1792. Min Range: -5.1792
Max Act: 4.6792. Min Act: -0.1700
Data Index: 2708993 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1792. Min Range: -5.1792
Max Act: 4.6792. Min Act: -0.1700
Data Index: 7107005 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1792. Min Range: -5.1792
Max Act: 4.6480. Min Act: -0.1700
Data Index: 2709003 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1792. Min Range: -5.1792
Max Act: 4.6480. Min Act: -0.1700
Data Index: 7761095 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1792. Min Range: -5.1792
Max Act: 4.6480. Min Act: -0.1700
Data Index: 1569611 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1792. Min Range: -5.1792
Max Act: 4.6167. Min Act: -0.1700
Data Index: 7905794 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1792. Min Range: -5.1792
Max Act: 4.6167. Min Act: -0.1700
Data Index: 6945601 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1792. Min Range: -5.1792
Max Act: 4.6167. Min Act: -0.1700
Data Index: 4379964 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1792. Min Range: -5.1792
Max Act: 4.5855. Min Act: -0.1700
Data Index: 1700879 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1792. Min Range: -5.1792
Max Act: 4.5542. Min Act: -0.1700
Data Index: 1992142 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1792. Min Range: -5.1792
Max Act: 4.5542. Min Act: -0.1700
Data Index: 295845 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1792. Min Range: -5.1792
Max Act: 4.5542. Min Act: -0.1700
Data Index: 3628903 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1792. Min Range: -5.1792
Max Act: 4.5542. Min Act: -0.1700
Data Index: 6232352 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1792. Min Range: -5.1792
Max Act: 4.5542. Min Act: -0.1700
Data Index: 7611687 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1792. Min Range: -5.1792
Max Act: 4.5229. Min Act: -0.1700
Data Index: 6643836 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19