Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 363 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.2851. Min Act: -0.1700
Data Index: 6202445 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.2537. Min Act: -0.1700
Data Index: 6036852 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.2851. Min Act: -0.1700
Data Index: 1207461 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.2222. Min Act: -0.1700
Data Index: 7300130 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.2065. Min Act: -0.1700
Data Index: 4578082 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.1751. Min Act: -0.1700
Data Index: 1703599 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.1908. Min Act: -0.1700
Data Index: 6589253 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.1751. Min Act: -0.1700
Data Index: 5203491 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.1908. Min Act: -0.1700
Data Index: 5203496 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.1593. Min Act: -0.1700
Data Index: 381894 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.1436. Min Act: -0.1700
Data Index: 2120188 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.1121. Min Act: -0.1700
Data Index: 4241474 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.1121. Min Act: -0.1700
Data Index: 3412100 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.0963. Min Act: -0.1700
Data Index: 7579517 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.0806. Min Act: -0.1700
Data Index: 57737 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.0963. Min Act: -0.1700
Data Index: 4232879 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.0963. Min Act: -0.1700
Data Index: 7483257 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.0963. Min Act: -0.1700
Data Index: 3414687 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.0963. Min Act: -0.1700
Data Index: 6028360 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2851. Min Range: -3.2851
Max Act: 3.0963. Min Act: -0.1700
Data Index: 8315001 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19