Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4612 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1405. Min Range: -5.1405
Max Act: 5.1405. Min Act: -0.1700
Data Index: 8408515 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1405. Min Range: -5.1405
Max Act: 5.0780. Min Act: -0.1700
Data Index: 7196757 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1405. Min Range: -5.1405
Max Act: 5.0155. Min Act: -0.1700
Data Index: 3661392 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1405. Min Range: -5.1405
Max Act: 4.9842. Min Act: -0.1700
Data Index: 1896679 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1405. Min Range: -5.1405
Max Act: 4.9530. Min Act: -0.1700
Data Index: 1287413 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1405. Min Range: -5.1405
Max Act: 4.9530. Min Act: -0.1700
Data Index: 7821838 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1405. Min Range: -5.1405
Max Act: 4.9217. Min Act: -0.1700
Data Index: 4416238 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1405. Min Range: -5.1405
Max Act: 4.8905. Min Act: -0.1700
Data Index: 832950 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1405. Min Range: -5.1405
Max Act: 4.8905. Min Act: -0.1700
Data Index: 1020162 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1405. Min Range: -5.1405
Max Act: 4.8592. Min Act: -0.1700
Data Index: 1220833 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1405. Min Range: -5.1405
Max Act: 4.8592. Min Act: -0.1700
Data Index: 7070701 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1405. Min Range: -5.1405
Max Act: 4.8280. Min Act: -0.1700
Data Index: 8608000 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1405. Min Range: -5.1405
Max Act: 4.7655. Min Act: -0.1700
Data Index: 2783775 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1405. Min Range: -5.1405
Max Act: 4.7655. Min Act: -0.1700
Data Index: 4100700 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1405. Min Range: -5.1405
Max Act: 4.7655. Min Act: -0.1700
Data Index: 3661408 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1405. Min Range: -5.1405
Max Act: 4.7655. Min Act: -0.1700
Data Index: 7565507 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1405. Min Range: -5.1405
Max Act: 4.7342. Min Act: -0.1700
Data Index: 8271087 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1405. Min Range: -5.1405
Max Act: 4.7342. Min Act: -0.1700
Data Index: 5941232 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1405. Min Range: -5.1405
Max Act: 4.7655. Min Act: -0.1700
Data Index: 8013211 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1405. Min Range: -5.1405
Max Act: 4.7655. Min Act: -0.1700
Data Index: 5454610 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19