Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4873 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3303. Min Range: -5.3303
Max Act: 5.3303. Min Act: -0.1700
Data Index: 7244688 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3303. Min Range: -5.3303
Max Act: 5.1740. Min Act: -0.1700
Data Index: 2320132 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3303. Min Range: -5.3303
Max Act: 5.0803. Min Act: -0.1700
Data Index: 6224017 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3303. Min Range: -5.3303
Max Act: 5.0490. Min Act: -0.1700
Data Index: 8203453 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3303. Min Range: -5.3303
Max Act: 4.8928. Min Act: -0.1700
Data Index: 5159351 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3303. Min Range: -5.3303
Max Act: 4.7678. Min Act: -0.1700
Data Index: 1698961 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3303. Min Range: -5.3303
Max Act: 4.7678. Min Act: -0.1700
Data Index: 3843903 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3303. Min Range: -5.3303
Max Act: 4.7365. Min Act: -0.1700
Data Index: 3945550 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3303. Min Range: -5.3303
Max Act: 4.7053. Min Act: -0.1700
Data Index: 3945544 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3303. Min Range: -5.3303
Max Act: 4.6740. Min Act: -0.1700
Data Index: 1051403 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3303. Min Range: -5.3303
Max Act: 4.5803. Min Act: -0.1700
Data Index: 8417739 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3303. Min Range: -5.3303
Max Act: 4.6115. Min Act: -0.1700
Data Index: 8224230 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3303. Min Range: -5.3303
Max Act: 4.5490. Min Act: -0.1700
Data Index: 4046492 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3303. Min Range: -5.3303
Max Act: 4.5178. Min Act: -0.1700
Data Index: 5498176 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3303. Min Range: -5.3303
Max Act: 4.5178. Min Act: -0.1700
Data Index: 5785596 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3303. Min Range: -5.3303
Max Act: 4.5178. Min Act: -0.1700
Data Index: 2573073 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3303. Min Range: -5.3303
Max Act: 4.5490. Min Act: -0.1700
Data Index: 1845750 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3303. Min Range: -5.3303
Max Act: 4.5178. Min Act: -0.1700
Data Index: 3168493 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3303. Min Range: -5.3303
Max Act: 4.4865. Min Act: -0.1700
Data Index: 7132481 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3303. Min Range: -5.3303
Max Act: 4.4865. Min Act: -0.1700
Data Index: 951836 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19