Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3281 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2502. Min Range: -5.2502
Max Act: 5.2502. Min Act: -0.1700
Data Index: 4561398 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2502. Min Range: -5.2502
Max Act: 5.1564. Min Act: -0.1700
Data Index: 6142700 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2502. Min Range: -5.2502
Max Act: 5.1564. Min Act: -0.1700
Data Index: 1016798 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2502. Min Range: -5.2502
Max Act: 5.1252. Min Act: -0.1700
Data Index: 416439 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2502. Min Range: -5.2502
Max Act: 5.0627. Min Act: -0.1700
Data Index: 6580051 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2502. Min Range: -5.2502
Max Act: 5.0314. Min Act: -0.1700
Data Index: 3395695 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2502. Min Range: -5.2502
Max Act: 5.0314. Min Act: -0.1700
Data Index: 8415638 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2502. Min Range: -5.2502
Max Act: 5.0314. Min Act: -0.1700
Data Index: 6487345 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2502. Min Range: -5.2502
Max Act: 5.0002. Min Act: -0.1700
Data Index: 8623990 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.9689. Min Act: -0.1700
Data Index: 7694245 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2502. Min Range: -5.2502
Max Act: 5.0002. Min Act: -0.1700
Data Index: 4263054 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2502. Min Range: -5.2502
Max Act: 5.0002. Min Act: -0.1700
Data Index: 3092900 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2502. Min Range: -5.2502
Max Act: 5.0002. Min Act: -0.1700
Data Index: 4321328 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2502. Min Range: -5.2502
Max Act: 5.0002. Min Act: -0.1700
Data Index: 7378061 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.9689. Min Act: -0.1700
Data Index: 8650637 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.9689. Min Act: -0.1700
Data Index: 5802101 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.9689. Min Act: -0.1700
Data Index: 1777130 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.9689. Min Act: -0.1700
Data Index: 306053 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2502. Min Range: -5.2502
Max Act: 5.0002. Min Act: -0.1700
Data Index: 6384157 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2502. Min Range: -5.2502
Max Act: 4.9377. Min Act: -0.1700
Data Index: 3428632 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19