Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3783 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2770. Min Range: -9.2770
Max Act: 9.2770. Min Act: -0.1700
Data Index: 1266087 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2770. Min Range: -9.2770
Max Act: 9.2770. Min Act: -0.1700
Data Index: 7266749 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2770. Min Range: -9.2770
Max Act: 9.2145. Min Act: -0.1700
Data Index: 7947707 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2770. Min Range: -9.2770
Max Act: 9.1520. Min Act: -0.1700
Data Index: 6637877 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2770. Min Range: -9.2770
Max Act: 9.1520. Min Act: -0.1700
Data Index: 1278986 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2770. Min Range: -9.2770
Max Act: 9.0895. Min Act: -0.1700
Data Index: 1991034 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2770. Min Range: -9.2770
Max Act: 9.0270. Min Act: -0.1700
Data Index: 2382657 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2770. Min Range: -9.2770
Max Act: 9.0270. Min Act: -0.1700
Data Index: 4381023 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2770. Min Range: -9.2770
Max Act: 8.9645. Min Act: -0.1700
Data Index: 8794780 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2770. Min Range: -9.2770
Max Act: 8.8395. Min Act: -0.1700
Data Index: 6404255 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2770. Min Range: -9.2770
Max Act: 8.8395. Min Act: -0.1700
Data Index: 1751602 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2770. Min Range: -9.2770
Max Act: 8.8395. Min Act: -0.1700
Data Index: 1767057 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2770. Min Range: -9.2770
Max Act: 8.8395. Min Act: -0.1700
Data Index: 322835 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2770. Min Range: -9.2770
Max Act: 8.7770. Min Act: -0.1700
Data Index: 2310553 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2770. Min Range: -9.2770
Max Act: 8.8395. Min Act: -0.1700
Data Index: 8150684 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2770. Min Range: -9.2770
Max Act: 8.7770. Min Act: -0.1700
Data Index: 8431724 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2770. Min Range: -9.2770
Max Act: 8.7770. Min Act: -0.1700
Data Index: 4844672 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2770. Min Range: -9.2770
Max Act: 8.7145. Min Act: -0.1700
Data Index: 4998262 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2770. Min Range: -9.2770
Max Act: 8.7145. Min Act: -0.1700
Data Index: 3328831 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2770. Min Range: -9.2770
Max Act: 8.7145. Min Act: -0.1700
Data Index: 319169 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19