Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4085 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.7119. Min Act: -0.1700
Data Index: 4131056 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.7119. Min Act: -0.1700
Data Index: 1439013 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.6806. Min Act: -0.1700
Data Index: 2510316 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.6493. Min Act: -0.1700
Data Index: 1741381 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.6493. Min Act: -0.1700
Data Index: 1580540 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.6181. Min Act: -0.1700
Data Index: 5269930 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.5556. Min Act: -0.1700
Data Index: 6814890 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.5243. Min Act: -0.1700
Data Index: 3133728 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.5243. Min Act: -0.1700
Data Index: 320193 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.4931. Min Act: -0.1700
Data Index: 7504678 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.4618. Min Act: -0.1700
Data Index: 5720934 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.4618. Min Act: -0.1700
Data Index: 5033206 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.4306. Min Act: -0.1700
Data Index: 506623 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.4306. Min Act: -0.1700
Data Index: 2341138 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.3681. Min Act: -0.1700
Data Index: 6722028 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.3993. Min Act: -0.1700
Data Index: 1050704 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.4306. Min Act: -0.1700
Data Index: 5482930 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.3993. Min Act: -0.1700
Data Index: 1636875 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.3993. Min Act: -0.1700
Data Index: 738185 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7119. Min Range: -4.7119
Max Act: 4.4306. Min Act: -0.1700
Data Index: 2510315 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19