Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3093 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.7519. Min Act: -0.1700
Data Index: 5477467 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.6424. Min Act: -0.1700
Data Index: 5477476 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.5798. Min Act: -0.1700
Data Index: 6622489 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.5798. Min Act: -0.1700
Data Index: 5477459 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.5015. Min Act: -0.1700
Data Index: 7146382 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.4859. Min Act: -0.1700
Data Index: 2687467 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.4859. Min Act: -0.1700
Data Index: 8221573 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.4702. Min Act: -0.1700
Data Index: 4157010 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.3448. Min Act: -0.1700
Data Index: 3130767 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.3291. Min Act: -0.1700
Data Index: 2699730 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.3134. Min Act: -0.1700
Data Index: 5863985 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.2820. Min Act: -0.1700
Data Index: 3951224 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.2663. Min Act: -0.1700
Data Index: 3013869 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.2506. Min Act: -0.1700
Data Index: 4902839 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.2663. Min Act: -0.1700
Data Index: 474302 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.2506. Min Act: -0.1700
Data Index: 150052 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.2191. Min Act: -0.1700
Data Index: 1717172 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.2191. Min Act: -0.1700
Data Index: 2427362 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.2034. Min Act: -0.1700
Data Index: 7012998 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7519. Min Range: -3.7519
Max Act: 3.1877. Min Act: -0.1700
Data Index: 1207891 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19