Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3463 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.7922. Min Act: -0.1700
Data Index: 3334345 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.7297. Min Act: -0.1700
Data Index: 7887769 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.6672. Min Act: -0.1700
Data Index: 4231817 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.6359. Min Act: -0.1700
Data Index: 1788384 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.6359. Min Act: -0.1700
Data Index: 5069202 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.4797. Min Act: -0.1700
Data Index: 8830816 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.5109. Min Act: -0.1700
Data Index: 2567554 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.4484. Min Act: -0.1700
Data Index: 7476135 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.4484. Min Act: -0.1700
Data Index: 539176 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.4172. Min Act: -0.1700
Data Index: 6030973 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.4172. Min Act: -0.1700
Data Index: 1407688 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.4172. Min Act: -0.1700
Data Index: 4080604 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.4172. Min Act: -0.1700
Data Index: 3491116 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.3859. Min Act: -0.1700
Data Index: 1442925 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.3859. Min Act: -0.1700
Data Index: 6744914 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.3859. Min Act: -0.1700
Data Index: 1171630 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.3234. Min Act: -0.1700
Data Index: 6003197 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.3234. Min Act: -0.1700
Data Index: 164269 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.2922. Min Act: -0.1700
Data Index: 6315343 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7922. Min Range: -5.7922
Max Act: 5.2609. Min Act: -0.1700
Data Index: 2179820 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19