Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2676 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.8958. Min Act: -0.1700
Data Index: 285498 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.8645. Min Act: -0.1700
Data Index: 871489 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.6770. Min Act: -0.1700
Data Index: 7111025 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.5833. Min Act: -0.1700
Data Index: 1411655 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.5833. Min Act: -0.1700
Data Index: 2941082 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.4583. Min Act: -0.1700
Data Index: 1040241 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.4270. Min Act: -0.1700
Data Index: 6103302 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.4270. Min Act: -0.1700
Data Index: 8600432 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.4270. Min Act: -0.1700
Data Index: 5207554 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.3958. Min Act: -0.1700
Data Index: 5414 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.3958. Min Act: -0.1700
Data Index: 6563497 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.3958. Min Act: -0.1700
Data Index: 3061334 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.3958. Min Act: -0.1700
Data Index: 937720 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.3645. Min Act: -0.1700
Data Index: 5308698 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.3645. Min Act: -0.1700
Data Index: 796483 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.3958. Min Act: -0.1700
Data Index: 5746459 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.3645. Min Act: -0.1700
Data Index: 5867188 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.3333. Min Act: -0.1700
Data Index: 452579 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.3333. Min Act: -0.1700
Data Index: 8386623 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8958. Min Range: -6.8958
Max Act: 6.2708. Min Act: -0.1700
Data Index: 5611672 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19