Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2876 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3606. Min Range: -7.3606
Max Act: 7.3606. Min Act: -0.1700
Data Index: 4974983 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3606. Min Range: -7.3606
Max Act: 7.2668. Min Act: -0.1700
Data Index: 3994901 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3606. Min Range: -7.3606
Max Act: 7.1418. Min Act: -0.1700
Data Index: 4974985 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3606. Min Range: -7.3606
Max Act: 7.0168. Min Act: -0.1700
Data Index: 2234932 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.8918. Min Act: -0.1700
Data Index: 3585733 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.8918. Min Act: -0.1700
Data Index: 8345869 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.8606. Min Act: -0.1700
Data Index: 3538715 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.8606. Min Act: -0.1700
Data Index: 2770268 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.8293. Min Act: -0.1700
Data Index: 5914954 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.8293. Min Act: -0.1700
Data Index: 2772753 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.8293. Min Act: -0.1700
Data Index: 1440947 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.7668. Min Act: -0.1700
Data Index: 2395054 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.7668. Min Act: -0.1700
Data Index: 5907642 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.7668. Min Act: -0.1700
Data Index: 846583 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.7668. Min Act: -0.1700
Data Index: 3738458 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.7668. Min Act: -0.1700
Data Index: 3601636 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.7356. Min Act: -0.1700
Data Index: 220230 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.7356. Min Act: -0.1700
Data Index: 8569735 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.7356. Min Act: -0.1700
Data Index: 2852352 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3606. Min Range: -7.3606
Max Act: 6.7043. Min Act: -0.1700
Data Index: 6411709 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19