Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3450 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.8156. Min Act: -0.1699
Data Index: 7842328 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.7844. Min Act: -0.1700
Data Index: 6494148 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.7531. Min Act: -0.1700
Data Index: 8665759 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.7219. Min Act: -0.1699
Data Index: 4463109 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.6906. Min Act: -0.1700
Data Index: 4653269 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.6594. Min Act: -0.1700
Data Index: 478765 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.5969. Min Act: -0.1700
Data Index: 6494146 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.6281. Min Act: -0.1700
Data Index: 7320805 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.5969. Min Act: -0.1700
Data Index: 5672523 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.5969. Min Act: -0.1700
Data Index: 5419106 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.5656. Min Act: -0.1700
Data Index: 6212786 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.5656. Min Act: -0.1700
Data Index: 6851410 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.5656. Min Act: -0.1700
Data Index: 8253742 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.5656. Min Act: -0.1700
Data Index: 5718994 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.5656. Min Act: -0.1700
Data Index: 5899177 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.5656. Min Act: -0.1700
Data Index: 5803883 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.5656. Min Act: -0.1700
Data Index: 4188435 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.5344. Min Act: -0.1700
Data Index: 2828977 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.5344. Min Act: -0.1700
Data Index: 3952677 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8156. Min Range: -4.8156
Max Act: 4.5344. Min Act: -0.1700
Data Index: 4779238 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19