Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4857 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2041. Min Range: -6.2041
Max Act: 6.2041. Min Act: -0.1700
Data Index: 7561343 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2041. Min Range: -6.2041
Max Act: 6.1728. Min Act: -0.1700
Data Index: 3824340 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2041. Min Range: -6.2041
Max Act: 6.0166. Min Act: -0.1700
Data Index: 1944902 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2041. Min Range: -6.2041
Max Act: 5.9853. Min Act: -0.1700
Data Index: 796782 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2041. Min Range: -6.2041
Max Act: 5.9228. Min Act: -0.1700
Data Index: 7960602 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2041. Min Range: -6.2041
Max Act: 5.9228. Min Act: -0.1700
Data Index: 5657011 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2041. Min Range: -6.2041
Max Act: 5.9228. Min Act: -0.1700
Data Index: 233535 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2041. Min Range: -6.2041
Max Act: 5.9228. Min Act: -0.1700
Data Index: 2120174 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2041. Min Range: -6.2041
Max Act: 5.9228. Min Act: -0.1700
Data Index: 7811455 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2041. Min Range: -6.2041
Max Act: 5.9228. Min Act: -0.1700
Data Index: 3682419 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2041. Min Range: -6.2041
Max Act: 5.9228. Min Act: -0.1700
Data Index: 3299568 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2041. Min Range: -6.2041
Max Act: 5.9228. Min Act: -0.1700
Data Index: 6300704 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2041. Min Range: -6.2041
Max Act: 5.9541. Min Act: -0.1700
Data Index: 5854566 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2041. Min Range: -6.2041
Max Act: 5.9228. Min Act: -0.1700
Data Index: 4541576 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2041. Min Range: -6.2041
Max Act: 5.8603. Min Act: -0.1700
Data Index: 2120173 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2041. Min Range: -6.2041
Max Act: 5.8916. Min Act: -0.1700
Data Index: 4487052 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2041. Min Range: -6.2041
Max Act: 5.8916. Min Act: -0.1700
Data Index: 4487049 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2041. Min Range: -6.2041
Max Act: 5.8916. Min Act: -0.1700
Data Index: 3209060 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2041. Min Range: -6.2041
Max Act: 5.8916. Min Act: -0.1700
Data Index: 1024071 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2041. Min Range: -6.2041
Max Act: 5.8916. Min Act: -0.1700
Data Index: 3209062 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19