Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4383 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7733. Min Range: -5.7733
Max Act: 5.7733. Min Act: -0.1700
Data Index: 5573609 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7733. Min Range: -5.7733
Max Act: 5.5858. Min Act: -0.1700
Data Index: 437308 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7733. Min Range: -5.7733
Max Act: 5.5233. Min Act: -0.1700
Data Index: 2512993 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7733. Min Range: -5.7733
Max Act: 5.1483. Min Act: -0.1700
Data Index: 3235196 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7733. Min Range: -5.7733
Max Act: 5.0545. Min Act: -0.1700
Data Index: 8062398 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7733. Min Range: -5.7733
Max Act: 5.0233. Min Act: -0.1700
Data Index: 4574891 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7733. Min Range: -5.7733
Max Act: 5.0545. Min Act: -0.1700
Data Index: 7116158 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7733. Min Range: -5.7733
Max Act: 5.0233. Min Act: -0.1700
Data Index: 1558432 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7733. Min Range: -5.7733
Max Act: 4.9608. Min Act: -0.1700
Data Index: 7896767 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7733. Min Range: -5.7733
Max Act: 4.9920. Min Act: -0.1700
Data Index: 2802639 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7733. Min Range: -5.7733
Max Act: 4.9920. Min Act: -0.1700
Data Index: 1426945 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7733. Min Range: -5.7733
Max Act: 4.9920. Min Act: -0.1700
Data Index: 2047931 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7733. Min Range: -5.7733
Max Act: 4.9920. Min Act: -0.1700
Data Index: 3775705 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7733. Min Range: -5.7733
Max Act: 4.9920. Min Act: -0.1700
Data Index: 3936385 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7733. Min Range: -5.7733
Max Act: 4.9608. Min Act: -0.1700
Data Index: 2769215 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7733. Min Range: -5.7733
Max Act: 4.9608. Min Act: -0.1700
Data Index: 7926573 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7733. Min Range: -5.7733
Max Act: 4.9608. Min Act: -0.1700
Data Index: 1650395 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7733. Min Range: -5.7733
Max Act: 4.9608. Min Act: -0.1700
Data Index: 3675350 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7733. Min Range: -5.7733
Max Act: 4.9920. Min Act: -0.1700
Data Index: 8024036 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7733. Min Range: -5.7733
Max Act: 4.9295. Min Act: -0.1700
Data Index: 321973 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19