Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3895 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0570. Min Range: -4.0570
Max Act: 4.0570. Min Act: -0.1700
Data Index: 3162614 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0570. Min Range: -4.0570
Max Act: 3.9945. Min Act: -0.1700
Data Index: 1443913 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0570. Min Range: -4.0570
Max Act: 3.9945. Min Act: -0.1700
Data Index: 1155520 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0570. Min Range: -4.0570
Max Act: 3.9320. Min Act: -0.1700
Data Index: 5297547 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0570. Min Range: -4.0570
Max Act: 3.9007. Min Act: -0.1700
Data Index: 1015881 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0570. Min Range: -4.0570
Max Act: 3.9007. Min Act: -0.1700
Data Index: 2553785 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0570. Min Range: -4.0570
Max Act: 3.9007. Min Act: -0.1700
Data Index: 4102151 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0570. Min Range: -4.0570
Max Act: 3.8695. Min Act: -0.1700
Data Index: 2663422 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0570. Min Range: -4.0570
Max Act: 3.8695. Min Act: -0.1700
Data Index: 965923 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0570. Min Range: -4.0570
Max Act: 3.8382. Min Act: -0.1700
Data Index: 8252207 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0570. Min Range: -4.0570
Max Act: 3.8538. Min Act: -0.1700
Data Index: 4102128 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0570. Min Range: -4.0570
Max Act: 3.8226. Min Act: -0.1700
Data Index: 7600415 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0570. Min Range: -4.0570
Max Act: 3.8069. Min Act: -0.1700
Data Index: 4102144 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0570. Min Range: -4.0570
Max Act: 3.7913. Min Act: -0.1700
Data Index: 4102130 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0570. Min Range: -4.0570
Max Act: 3.8069. Min Act: -0.1700
Data Index: 8051083 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0570. Min Range: -4.0570
Max Act: 3.7913. Min Act: -0.1700
Data Index: 6118553 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0570. Min Range: -4.0570
Max Act: 3.7756. Min Act: -0.1700
Data Index: 5959911 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0570. Min Range: -4.0570
Max Act: 3.7444. Min Act: -0.1700
Data Index: 3923911 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0570. Min Range: -4.0570
Max Act: 3.7600. Min Act: -0.1700
Data Index: 1133080 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0570. Min Range: -4.0570
Max Act: 3.7600. Min Act: -0.1700
Data Index: 5540736 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19