Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1790 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.4358. Min Act: -0.1700
Data Index: 8688349 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.4044. Min Act: -0.1700
Data Index: 7050692 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.4044. Min Act: -0.1700
Data Index: 2303745 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.3731. Min Act: -0.1700
Data Index: 8141887 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.3731. Min Act: -0.1700
Data Index: 2901290 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.3731. Min Act: -0.1700
Data Index: 7250789 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.3731. Min Act: -0.1700
Data Index: 1660478 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.3731. Min Act: -0.1700
Data Index: 6987367 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.3417. Min Act: -0.1700
Data Index: 3337439 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.3417. Min Act: -0.1700
Data Index: 5841384 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.3417. Min Act: -0.1700
Data Index: 1798968 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.3417. Min Act: -0.1700
Data Index: 2203641 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.3417. Min Act: -0.1700
Data Index: 6739276 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.3417. Min Act: -0.1700
Data Index: 4650806 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.3260. Min Act: -0.1700
Data Index: 5442568 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.3260. Min Act: -0.1700
Data Index: 966652 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.3260. Min Act: -0.1700
Data Index: 5272560 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.3260. Min Act: -0.1700
Data Index: 2731101 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.3260. Min Act: -0.1700
Data Index: 703510 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4358. Min Range: -3.4358
Max Act: 3.3260. Min Act: -0.1700
Data Index: 2853328 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19