Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3972 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.8553. Min Act: -0.1700
Data Index: 8633107 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.7303. Min Act: -0.1700
Data Index: 1022996 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.6991. Min Act: -0.1700
Data Index: 6655259 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.5116. Min Act: -0.1700
Data Index: 2118207 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.5116. Min Act: -0.1700
Data Index: 6539060 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.4491. Min Act: -0.1700
Data Index: 2935935 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.4178. Min Act: -0.1700
Data Index: 556614 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.3553. Min Act: -0.1700
Data Index: 3823852 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.3553. Min Act: -0.1700
Data Index: 6005442 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.2616. Min Act: -0.1700
Data Index: 7887272 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.2303. Min Act: -0.1700
Data Index: 2027048 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.2616. Min Act: -0.1700
Data Index: 6403106 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.2303. Min Act: -0.1700
Data Index: 4865515 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.2303. Min Act: -0.1700
Data Index: 7280134 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.2303. Min Act: -0.1700
Data Index: 3810080 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.1678. Min Act: -0.1700
Data Index: 1449251 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.1991. Min Act: -0.1700
Data Index: 7920856 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.1991. Min Act: -0.1700
Data Index: 6676040 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.1678. Min Act: -0.1700
Data Index: 8168025 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8553. Min Range: -6.8553
Max Act: 6.1678. Min Act: -0.1700
Data Index: 6380776 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19