Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3061 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3917. Min Range: -8.3917
Max Act: 8.3917. Min Act: -0.1700
Data Index: 5474809 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3917. Min Range: -8.3917
Max Act: 7.8292. Min Act: -0.1700
Data Index: 8222952 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3917. Min Range: -8.3917
Max Act: 7.8292. Min Act: -0.1700
Data Index: 5405673 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3917. Min Range: -8.3917
Max Act: 7.7042. Min Act: -0.1700
Data Index: 5474829 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3917. Min Range: -8.3917
Max Act: 7.6417. Min Act: -0.1700
Data Index: 523780 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3917. Min Range: -8.3917
Max Act: 7.6417. Min Act: -0.1700
Data Index: 7903786 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3917. Min Range: -8.3917
Max Act: 7.4854. Min Act: -0.1700
Data Index: 1910328 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3917. Min Range: -8.3917
Max Act: 7.4854. Min Act: -0.1700
Data Index: 2050526 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3917. Min Range: -8.3917
Max Act: 7.4542. Min Act: -0.1700
Data Index: 1214486 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3917. Min Range: -8.3917
Max Act: 7.4229. Min Act: -0.1700
Data Index: 5474808 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3917. Min Range: -8.3917
Max Act: 7.3604. Min Act: -0.1700
Data Index: 1635920 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3917. Min Range: -8.3917
Max Act: 7.3604. Min Act: -0.1700
Data Index: 6143063 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3917. Min Range: -8.3917
Max Act: 7.3604. Min Act: -0.1700
Data Index: 5423393 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3917. Min Range: -8.3917
Max Act: 7.3604. Min Act: -0.1700
Data Index: 3265980 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3917. Min Range: -8.3917
Max Act: 7.2979. Min Act: -0.1700
Data Index: 5819965 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3917. Min Range: -8.3917
Max Act: 7.3292. Min Act: -0.1700
Data Index: 2167753 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3917. Min Range: -8.3917
Max Act: 7.2979. Min Act: -0.1700
Data Index: 5253990 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3917. Min Range: -8.3917
Max Act: 7.2979. Min Act: -0.1700
Data Index: 7163899 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3917. Min Range: -8.3917
Max Act: 7.2979. Min Act: -0.1700
Data Index: 7812988 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3917. Min Range: -8.3917
Max Act: 7.2979. Min Act: -0.1700
Data Index: 29257 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19