Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 517 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.9054. Min Act: -0.1700
Data Index: 1199050 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.9367. Min Act: -0.1700
Data Index: 6341681 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.8429. Min Act: -0.1700
Data Index: 4428234 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.7492. Min Act: -0.1700
Data Index: 6893379 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.7179. Min Act: -0.1700
Data Index: 8681183 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.5929. Min Act: -0.1700
Data Index: 2068078 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.5304. Min Act: -0.1700
Data Index: 3599031 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.5304. Min Act: -0.1700
Data Index: 6268532 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.4992. Min Act: -0.1700
Data Index: 4588120 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.5304. Min Act: -0.1700
Data Index: 6614629 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.4679. Min Act: -0.1700
Data Index: 5928337 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.4679. Min Act: -0.1700
Data Index: 5807495 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.4367. Min Act: -0.1700
Data Index: 1983663 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.4367. Min Act: -0.1700
Data Index: 2546816 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.4054. Min Act: -0.1700
Data Index: 6893380 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.4054. Min Act: -0.1700
Data Index: 7392700 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.3429. Min Act: -0.1700
Data Index: 5517554 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.3742. Min Act: -0.1700
Data Index: 2373164 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.3429. Min Act: -0.1700
Data Index: 7914179 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9367. Min Range: -7.9367
Max Act: 7.3117. Min Act: -0.1700
Data Index: 5453046 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19