Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9556. Min Range: -7.9556
Max Act: 7.9556. Min Act: -0.1700
Data Index: 8272963 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9556. Min Range: -7.9556
Max Act: 7.6118. Min Act: -0.1700
Data Index: 310793 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9556. Min Range: -7.9556
Max Act: 7.3931. Min Act: -0.1700
Data Index: 4432040 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9556. Min Range: -7.9556
Max Act: 7.2993. Min Act: -0.1700
Data Index: 5367619 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9556. Min Range: -7.9556
Max Act: 7.1118. Min Act: -0.1700
Data Index: 5024273 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9556. Min Range: -7.9556
Max Act: 7.0806. Min Act: -0.1700
Data Index: 4034641 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9556. Min Range: -7.9556
Max Act: 7.0181. Min Act: -0.1700
Data Index: 6476021 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9556. Min Range: -7.9556
Max Act: 6.9868. Min Act: -0.1700
Data Index: 1857314 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9556. Min Range: -7.9556
Max Act: 6.9556. Min Act: -0.1700
Data Index: 8430184 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9556. Min Range: -7.9556
Max Act: 6.9243. Min Act: -0.1700
Data Index: 8452598 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9556. Min Range: -7.9556
Max Act: 6.9243. Min Act: -0.1700
Data Index: 4663837 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9556. Min Range: -7.9556
Max Act: 6.9243. Min Act: -0.1700
Data Index: 5141523 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9556. Min Range: -7.9556
Max Act: 6.9243. Min Act: -0.1700
Data Index: 5752503 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9556. Min Range: -7.9556
Max Act: 6.9243. Min Act: -0.1700
Data Index: 8512521 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9556. Min Range: -7.9556
Max Act: 6.9243. Min Act: -0.1700
Data Index: 736617 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9556. Min Range: -7.9556
Max Act: 6.8618. Min Act: -0.1700
Data Index: 2022603 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9556. Min Range: -7.9556
Max Act: 6.8618. Min Act: -0.1700
Data Index: 7624389 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9556. Min Range: -7.9556
Max Act: 6.8618. Min Act: -0.1700
Data Index: 8793621 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9556. Min Range: -7.9556
Max Act: 6.8306. Min Act: -0.1700
Data Index: 376728 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9556. Min Range: -7.9556
Max Act: 6.7993. Min Act: -0.1700
Data Index: 887502 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19