Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2967 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.9986. Min Act: -0.1700
Data Index: 539120 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.8111. Min Act: -0.1700
Data Index: 2424628 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.8423. Min Act: -0.1700
Data Index: 654989 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.8111. Min Act: -0.1700
Data Index: 8326196 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.7486. Min Act: -0.1700
Data Index: 3795379 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.7798. Min Act: -0.1700
Data Index: 449182 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.7173. Min Act: -0.1700
Data Index: 1884198 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.7173. Min Act: -0.1700
Data Index: 2149613 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.7486. Min Act: -0.1700
Data Index: 4734865 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.6861. Min Act: -0.1700
Data Index: 8318988 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.6861. Min Act: -0.1700
Data Index: 1644015 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.6861. Min Act: -0.1700
Data Index: 1618953 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.6548. Min Act: -0.1700
Data Index: 1569887 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.6548. Min Act: -0.1700
Data Index: 8066086 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.6548. Min Act: -0.1700
Data Index: 4495596 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.6548. Min Act: -0.1700
Data Index: 5785826 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.6548. Min Act: -0.1700
Data Index: 8464091 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.6236. Min Act: -0.1700
Data Index: 7195142 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.6236. Min Act: -0.1700
Data Index: 7195144 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9986. Min Range: -5.9986
Max Act: 5.6236. Min Act: -0.1700
Data Index: 656459 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19