Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.9938. Min Act: -0.1700
Data Index: 201251 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.9591. Min Act: -0.1700
Data Index: 408657 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.9678. Min Act: -0.1700
Data Index: 6650239 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.9505. Min Act: -0.1700
Data Index: 1491416 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.9419. Min Act: -0.1700
Data Index: 4048187 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.9161. Min Act: -0.1699
Data Index: 3597604 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.9161. Min Act: -0.1700
Data Index: 170317 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.9161. Min Act: -0.1700
Data Index: 5511561 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.9247. Min Act: -0.1695
Data Index: 6836970 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.8990. Min Act: -0.1700
Data Index: 170316 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.8734. Min Act: -0.1700
Data Index: 170318 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.8564. Min Act: -0.1700
Data Index: 8662775 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.8734. Min Act: -0.1700
Data Index: 1757880 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.8649. Min Act: -0.1700
Data Index: 5255925 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.8649. Min Act: -0.1700
Data Index: 8273121 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.8649. Min Act: -0.1697
Data Index: 2112177 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.8734. Min Act: -0.1700
Data Index: 5889372 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.8649. Min Act: -0.1699
Data Index: 900128 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.8564. Min Act: -0.1700
Data Index: 6129508 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9938. Min Range: -0.9938
Max Act: 0.8649. Min Act: -0.1700
Data Index: 5190748 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19