Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1787 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.9041. Min Act: -0.1700
Data Index: 5081326 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.8729. Min Act: -0.1700
Data Index: 1311942 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.8416. Min Act: -0.1700
Data Index: 7152003 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.8416. Min Act: -0.1700
Data Index: 6700525 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.8104. Min Act: -0.1700
Data Index: 1955347 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.8104. Min Act: -0.1700
Data Index: 3141608 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.7479. Min Act: -0.1700
Data Index: 3785156 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.7791. Min Act: -0.1700
Data Index: 3826114 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.7479. Min Act: -0.1700
Data Index: 4449823 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.7479. Min Act: -0.1700
Data Index: 1595469 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.7479. Min Act: -0.1700
Data Index: 6304416 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.6854. Min Act: -0.1700
Data Index: 6581822 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.6854. Min Act: -0.1700
Data Index: 4570727 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.6541. Min Act: -0.1700
Data Index: 148413 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.6541. Min Act: -0.1700
Data Index: 5166036 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.6541. Min Act: -0.1700
Data Index: 5900670 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.6229. Min Act: -0.1700
Data Index: 3441053 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.5604. Min Act: -0.1700
Data Index: 8335906 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.5916. Min Act: -0.1700
Data Index: 714519 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9041. Min Range: -5.9041
Max Act: 5.5916. Min Act: -0.1700
Data Index: 6203620 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19