Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3745 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2224. Min Range: -2.2224
Max Act: 2.2224. Min Act: -0.1700
Data Index: 4408455 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2224. Min Range: -2.2224
Max Act: 1.5923. Min Act: -0.1700
Data Index: 638612 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2224. Min Range: -2.2224
Max Act: 1.5748. Min Act: -0.1700
Data Index: 7223499 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2224. Min Range: -2.2224
Max Act: 1.5398. Min Act: -0.1700
Data Index: 6781902 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2224. Min Range: -2.2224
Max Act: 1.5223. Min Act: -0.1699
Data Index: 883431 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2224. Min Range: -2.2224
Max Act: 1.5398. Min Act: -0.1700
Data Index: 4077515 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2224. Min Range: -2.2224
Max Act: 1.4696. Min Act: -0.1700
Data Index: 6854302 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2224. Min Range: -2.2224
Max Act: 1.4871. Min Act: -0.1700
Data Index: 3948093 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2224. Min Range: -2.2224
Max Act: 1.4520. Min Act: -0.1679
Data Index: 2637693 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2224. Min Range: -2.2224
Max Act: 1.4520. Min Act: -0.1700
Data Index: 8353733 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2224. Min Range: -2.2224
Max Act: 1.4168. Min Act: -0.1696
Data Index: 5422072 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2224. Min Range: -2.2224
Max Act: 1.4168. Min Act: -0.1700
Data Index: 4743626 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2224. Min Range: -2.2224
Max Act: 1.3992. Min Act: -0.1700
Data Index: 5102457 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2224. Min Range: -2.2224
Max Act: 1.3815. Min Act: -0.1700
Data Index: 1338767 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2224. Min Range: -2.2224
Max Act: 1.3992. Min Act: -0.1700
Data Index: 5066199 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2224. Min Range: -2.2224
Max Act: 1.3815. Min Act: -0.1700
Data Index: 4419041 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2224. Min Range: -2.2224
Max Act: 1.3815. Min Act: -0.1699
Data Index: 2844760 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2224. Min Range: -2.2224
Max Act: 1.3463. Min Act: -0.1696
Data Index: 5084930 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2224. Min Range: -2.2224
Max Act: 1.3639. Min Act: -0.1700
Data Index: 4862104 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2224. Min Range: -2.2224
Max Act: 1.3815. Min Act: -0.1700
Data Index: 5432630 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19