Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2521 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1556. Min Range: -8.1556
Max Act: 8.1556. Min Act: -0.1700
Data Index: 1341325 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1556. Min Range: -8.1556
Max Act: 8.0931. Min Act: -0.1700
Data Index: 2447379 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1556. Min Range: -8.1556
Max Act: 7.7806. Min Act: -0.1700
Data Index: 380661 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1556. Min Range: -8.1556
Max Act: 7.6556. Min Act: -0.1700
Data Index: 3004586 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1556. Min Range: -8.1556
Max Act: 7.7181. Min Act: -0.1700
Data Index: 4945808 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1556. Min Range: -8.1556
Max Act: 7.6556. Min Act: -0.1700
Data Index: 8031706 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1556. Min Range: -8.1556
Max Act: 7.6556. Min Act: -0.1700
Data Index: 2343466 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1556. Min Range: -8.1556
Max Act: 7.6243. Min Act: -0.1700
Data Index: 4908365 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1556. Min Range: -8.1556
Max Act: 7.6243. Min Act: -0.1700
Data Index: 8271592 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1556. Min Range: -8.1556
Max Act: 7.6243. Min Act: -0.1700
Data Index: 314194 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1556. Min Range: -8.1556
Max Act: 7.5931. Min Act: -0.1700
Data Index: 2265285 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1556. Min Range: -8.1556
Max Act: 7.5931. Min Act: -0.1700
Data Index: 8052522 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1556. Min Range: -8.1556
Max Act: 7.5618. Min Act: -0.1700
Data Index: 3282345 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1556. Min Range: -8.1556
Max Act: 7.5618. Min Act: -0.1700
Data Index: 3721111 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1556. Min Range: -8.1556
Max Act: 7.4681. Min Act: -0.1700
Data Index: 4519664 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1556. Min Range: -8.1556
Max Act: 7.4681. Min Act: -0.1700
Data Index: 7746858 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1556. Min Range: -8.1556
Max Act: 7.4681. Min Act: -0.1700
Data Index: 543162 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1556. Min Range: -8.1556
Max Act: 7.4681. Min Act: -0.1700
Data Index: 7047032 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1556. Min Range: -8.1556
Max Act: 7.4368. Min Act: -0.1700
Data Index: 7187533 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1556. Min Range: -8.1556
Max Act: 7.4368. Min Act: -0.1700
Data Index: 6969835 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19