Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2665 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1227. Min Range: -6.1227
Max Act: 6.1227. Min Act: -0.1700
Data Index: 4789109 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1227. Min Range: -6.1227
Max Act: 6.0602. Min Act: -0.1700
Data Index: 7560617 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1227. Min Range: -6.1227
Max Act: 6.0602. Min Act: -0.1700
Data Index: 1593166 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1227. Min Range: -6.1227
Max Act: 6.0290. Min Act: -0.1700
Data Index: 258576 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1227. Min Range: -6.1227
Max Act: 6.0290. Min Act: -0.1700
Data Index: 5639209 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1227. Min Range: -6.1227
Max Act: 6.0290. Min Act: -0.1700
Data Index: 1699779 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1227. Min Range: -6.1227
Max Act: 5.9977. Min Act: -0.1700
Data Index: 4511339 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1227. Min Range: -6.1227
Max Act: 5.9665. Min Act: -0.1700
Data Index: 7051639 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1227. Min Range: -6.1227
Max Act: 5.9352. Min Act: -0.1700
Data Index: 5464036 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1227. Min Range: -6.1227
Max Act: 5.9040. Min Act: -0.1700
Data Index: 7260891 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1227. Min Range: -6.1227
Max Act: 5.8727. Min Act: -0.1700
Data Index: 4901245 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1227. Min Range: -6.1227
Max Act: 5.8727. Min Act: -0.1700
Data Index: 4922501 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1227. Min Range: -6.1227
Max Act: 5.8415. Min Act: -0.1700
Data Index: 5105965 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1227. Min Range: -6.1227
Max Act: 5.8415. Min Act: -0.1700
Data Index: 5710659 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1227. Min Range: -6.1227
Max Act: 5.8415. Min Act: -0.1700
Data Index: 8614388 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1227. Min Range: -6.1227
Max Act: 5.8102. Min Act: -0.1700
Data Index: 7966629 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1227. Min Range: -6.1227
Max Act: 5.8102. Min Act: -0.1700
Data Index: 3023103 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1227. Min Range: -6.1227
Max Act: 5.7790. Min Act: -0.1700
Data Index: 5236406 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1227. Min Range: -6.1227
Max Act: 5.7790. Min Act: -0.1700
Data Index: 1052964 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1227. Min Range: -6.1227
Max Act: 5.7790. Min Act: -0.1700
Data Index: 6162795 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19