Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3186 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6278. Min Range: -5.6278
Max Act: 5.6278. Min Act: -0.1700
Data Index: 2801120 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6278. Min Range: -5.6278
Max Act: 5.2840. Min Act: -0.1700
Data Index: 2759018 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6278. Min Range: -5.6278
Max Act: 5.1903. Min Act: -0.1700
Data Index: 7823821 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6278. Min Range: -5.6278
Max Act: 5.1590. Min Act: -0.1700
Data Index: 1000009 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6278. Min Range: -5.6278
Max Act: 5.1278. Min Act: -0.1700
Data Index: 8595236 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6278. Min Range: -5.6278
Max Act: 5.0965. Min Act: -0.1700
Data Index: 7745194 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6278. Min Range: -5.6278
Max Act: 5.1278. Min Act: -0.1700
Data Index: 3692846 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6278. Min Range: -5.6278
Max Act: 5.1278. Min Act: -0.1700
Data Index: 2624146 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6278. Min Range: -5.6278
Max Act: 5.0965. Min Act: -0.1700
Data Index: 6973392 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6278. Min Range: -5.6278
Max Act: 5.0965. Min Act: -0.1700
Data Index: 3507948 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6278. Min Range: -5.6278
Max Act: 5.0653. Min Act: -0.1700
Data Index: 2186247 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6278. Min Range: -5.6278
Max Act: 5.0340. Min Act: -0.1700
Data Index: 1773226 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6278. Min Range: -5.6278
Max Act: 5.0340. Min Act: -0.1700
Data Index: 6174973 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6278. Min Range: -5.6278
Max Act: 5.0340. Min Act: -0.1700
Data Index: 1532976 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6278. Min Range: -5.6278
Max Act: 5.0028. Min Act: -0.1700
Data Index: 2918322 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6278. Min Range: -5.6278
Max Act: 5.0028. Min Act: -0.1700
Data Index: 1682556 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6278. Min Range: -5.6278
Max Act: 5.0028. Min Act: -0.1700
Data Index: 817655 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6278. Min Range: -5.6278
Max Act: 5.0028. Min Act: -0.1700
Data Index: 3265232 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6278. Min Range: -5.6278
Max Act: 5.0028. Min Act: -0.1700
Data Index: 6174978 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6278. Min Range: -5.6278
Max Act: 4.9403. Min Act: -0.1700
Data Index: 5413222 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19