Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2605 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2329. Min Range: -6.2329
Max Act: 6.2329. Min Act: -0.1700
Data Index: 636502 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2329. Min Range: -6.2329
Max Act: 6.1079. Min Act: -0.1700
Data Index: 3639629 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2329. Min Range: -6.2329
Max Act: 6.0454. Min Act: -0.1700
Data Index: 266506 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2329. Min Range: -6.2329
Max Act: 6.0767. Min Act: -0.1700
Data Index: 5045267 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2329. Min Range: -6.2329
Max Act: 6.0454. Min Act: -0.1700
Data Index: 1750117 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2329. Min Range: -6.2329
Max Act: 6.0454. Min Act: -0.1700
Data Index: 2551836 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2329. Min Range: -6.2329
Max Act: 6.0142. Min Act: -0.1700
Data Index: 5572200 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2329. Min Range: -6.2329
Max Act: 6.0142. Min Act: -0.1700
Data Index: 512113 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2329. Min Range: -6.2329
Max Act: 6.0142. Min Act: -0.1700
Data Index: 119195 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2329. Min Range: -6.2329
Max Act: 6.0142. Min Act: -0.1700
Data Index: 3625471 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.9829. Min Act: -0.1700
Data Index: 928934 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.9829. Min Act: -0.1700
Data Index: 3816539 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.9829. Min Act: -0.1700
Data Index: 2183187 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.9829. Min Act: -0.1700
Data Index: 7914194 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2329. Min Range: -6.2329
Max Act: 6.0142. Min Act: -0.1700
Data Index: 1595535 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.9829. Min Act: -0.1700
Data Index: 3366080 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.9517. Min Act: -0.1700
Data Index: 1517741 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.9204. Min Act: -0.1700
Data Index: 2324326 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.9517. Min Act: -0.1700
Data Index: 4255217 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2329. Min Range: -6.2329
Max Act: 5.9204. Min Act: -0.1700
Data Index: 5338412 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19