Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.5428. Min Act: -0.1700
Data Index: 7210970 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4178. Min Act: -0.1700
Data Index: 8581511 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.3553. Min Act: -0.1700
Data Index: 6041910 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.2928. Min Act: -0.1700
Data Index: 8110560 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.2928. Min Act: -0.1700
Data Index: 3323632 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.1990. Min Act: -0.1700
Data Index: 6175156 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.1990. Min Act: -0.1700
Data Index: 6011856 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.1678. Min Act: -0.1700
Data Index: 5023203 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.1678. Min Act: -0.1700
Data Index: 8182306 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.1678. Min Act: -0.1700
Data Index: 1197375 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.1678. Min Act: -0.1700
Data Index: 4301879 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.1365. Min Act: -0.1700
Data Index: 8417463 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.1365. Min Act: -0.1700
Data Index: 7183841 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.1365. Min Act: -0.1700
Data Index: 2412614 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.1365. Min Act: -0.1700
Data Index: 8498406 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.1365. Min Act: -0.1700
Data Index: 8201196 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.1365. Min Act: -0.1700
Data Index: 3674161 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.1365. Min Act: -0.1700
Data Index: 2346576 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.1365. Min Act: -0.1700
Data Index: 7713868 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.1053. Min Act: -0.1700
Data Index: 4306546 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19