Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3872 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0584. Min Range: -8.0584
Max Act: 8.0584. Min Act: -0.1700
Data Index: 2121648 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0584. Min Range: -8.0584
Max Act: 7.4334. Min Act: -0.1700
Data Index: 6633367 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0584. Min Range: -8.0584
Max Act: 7.4959. Min Act: -0.1700
Data Index: 2514296 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0584. Min Range: -8.0584
Max Act: 7.2459. Min Act: -0.1700
Data Index: 327420 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0584. Min Range: -8.0584
Max Act: 7.2146. Min Act: -0.1700
Data Index: 1332977 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0584. Min Range: -8.0584
Max Act: 7.1834. Min Act: -0.1700
Data Index: 98198 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0584. Min Range: -8.0584
Max Act: 7.1521. Min Act: -0.1700
Data Index: 3533853 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0584. Min Range: -8.0584
Max Act: 7.1521. Min Act: -0.1700
Data Index: 2151601 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0584. Min Range: -8.0584
Max Act: 7.1209. Min Act: -0.1700
Data Index: 2134854 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0584. Min Range: -8.0584
Max Act: 7.1209. Min Act: -0.1700
Data Index: 6054857 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0584. Min Range: -8.0584
Max Act: 7.1209. Min Act: -0.1700
Data Index: 5660669 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0584. Min Range: -8.0584
Max Act: 7.1209. Min Act: -0.1700
Data Index: 8032051 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0584. Min Range: -8.0584
Max Act: 7.0584. Min Act: -0.1700
Data Index: 1198176 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0584. Min Range: -8.0584
Max Act: 7.0896. Min Act: -0.1700
Data Index: 4175343 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0584. Min Range: -8.0584
Max Act: 7.0584. Min Act: -0.1700
Data Index: 3867494 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0584. Min Range: -8.0584
Max Act: 7.0584. Min Act: -0.1700
Data Index: 6549106 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0584. Min Range: -8.0584
Max Act: 7.0271. Min Act: -0.1700
Data Index: 5845368 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0584. Min Range: -8.0584
Max Act: 7.0584. Min Act: -0.1700
Data Index: 4383709 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0584. Min Range: -8.0584
Max Act: 7.0271. Min Act: -0.1700
Data Index: 5741524 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0584. Min Range: -8.0584
Max Act: 6.9959. Min Act: -0.1700
Data Index: 3890901 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19