Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3393 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.6534. Min Act: -0.1700
Data Index: 4350714 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.6534. Min Act: -0.1700
Data Index: 1096100 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.4659. Min Act: -0.1700
Data Index: 2977211 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.4659. Min Act: -0.1700
Data Index: 6466303 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.4034. Min Act: -0.1700
Data Index: 1865496 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.3096. Min Act: -0.1700
Data Index: 6663581 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.2784. Min Act: -0.1700
Data Index: 1865492 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.2159. Min Act: -0.1700
Data Index: 651067 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.1846. Min Act: -0.1700
Data Index: 1760500 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.1221. Min Act: -0.1700
Data Index: 4193824 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.1221. Min Act: -0.1700
Data Index: 542546 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.1221. Min Act: -0.1700
Data Index: 611870 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.0909. Min Act: -0.1700
Data Index: 5595474 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.0909. Min Act: -0.1700
Data Index: 2195671 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.0909. Min Act: -0.1700
Data Index: 5106074 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.0909. Min Act: -0.1700
Data Index: 6250621 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.0909. Min Act: -0.1700
Data Index: 5222332 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.0909. Min Act: -0.1700
Data Index: 8768007 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.0909. Min Act: -0.1700
Data Index: 1059845 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6534. Min Range: -6.6534
Max Act: 6.0596. Min Act: -0.1700
Data Index: 3228705 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19