Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3610 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4323. Min Range: -9.4323
Max Act: 9.4323. Min Act: -0.1700
Data Index: 5429480 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4323. Min Range: -9.4323
Max Act: 9.2448. Min Act: -0.1700
Data Index: 727923 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4323. Min Range: -9.4323
Max Act: 9.1823. Min Act: -0.1700
Data Index: 8786128 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4323. Min Range: -9.4323
Max Act: 9.1198. Min Act: -0.1700
Data Index: 6872505 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4323. Min Range: -9.4323
Max Act: 9.0573. Min Act: -0.1700
Data Index: 2942494 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4323. Min Range: -9.4323
Max Act: 8.9948. Min Act: -0.1700
Data Index: 8096164 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4323. Min Range: -9.4323
Max Act: 8.9948. Min Act: -0.1700
Data Index: 7513558 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4323. Min Range: -9.4323
Max Act: 8.9323. Min Act: -0.1700
Data Index: 682869 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4323. Min Range: -9.4323
Max Act: 8.9323. Min Act: -0.1700
Data Index: 1939371 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4323. Min Range: -9.4323
Max Act: 8.9323. Min Act: -0.1700
Data Index: 7348389 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4323. Min Range: -9.4323
Max Act: 8.9323. Min Act: -0.1700
Data Index: 7216597 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4323. Min Range: -9.4323
Max Act: 8.9323. Min Act: -0.1700
Data Index: 4254205 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4323. Min Range: -9.4323
Max Act: 8.9323. Min Act: -0.1698
Data Index: 6817851 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4323. Min Range: -9.4323
Max Act: 8.9323. Min Act: -0.1700
Data Index: 670456 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4323. Min Range: -9.4323
Max Act: 8.8698. Min Act: -0.1700
Data Index: 1485129 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4323. Min Range: -9.4323
Max Act: 8.8698. Min Act: -0.1700
Data Index: 3712434 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4323. Min Range: -9.4323
Max Act: 8.8698. Min Act: -0.1700
Data Index: 1284760 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4323. Min Range: -9.4323
Max Act: 8.8698. Min Act: -0.1700
Data Index: 5506283 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4323. Min Range: -9.4323
Max Act: 8.8698. Min Act: -0.1700
Data Index: 1315187 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4323. Min Range: -9.4323
Max Act: 8.8698. Min Act: -0.1700
Data Index: 5910665 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19