Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4110 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4196. Min Range: -6.4196
Max Act: 6.4196. Min Act: -0.1700
Data Index: 7750451 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4196. Min Range: -6.4196
Max Act: 6.4196. Min Act: -0.1700
Data Index: 2042013 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4196. Min Range: -6.4196
Max Act: 6.3258. Min Act: -0.1700
Data Index: 3171916 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4196. Min Range: -6.4196
Max Act: 6.2633. Min Act: -0.1700
Data Index: 4115804 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4196. Min Range: -6.4196
Max Act: 6.2321. Min Act: -0.1700
Data Index: 7149602 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4196. Min Range: -6.4196
Max Act: 6.1383. Min Act: -0.1700
Data Index: 1772792 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4196. Min Range: -6.4196
Max Act: 6.1071. Min Act: -0.1700
Data Index: 2869026 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4196. Min Range: -6.4196
Max Act: 6.0758. Min Act: -0.1700
Data Index: 81369 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4196. Min Range: -6.4196
Max Act: 6.0758. Min Act: -0.1700
Data Index: 1972993 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4196. Min Range: -6.4196
Max Act: 6.0446. Min Act: -0.1700
Data Index: 2378805 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4196. Min Range: -6.4196
Max Act: 6.0133. Min Act: -0.1700
Data Index: 1085222 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4196. Min Range: -6.4196
Max Act: 5.9821. Min Act: -0.1700
Data Index: 7504356 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4196. Min Range: -6.4196
Max Act: 5.9508. Min Act: -0.1700
Data Index: 1351434 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4196. Min Range: -6.4196
Max Act: 5.9821. Min Act: -0.1700
Data Index: 6980857 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4196. Min Range: -6.4196
Max Act: 5.9508. Min Act: -0.1700
Data Index: 6662825 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4196. Min Range: -6.4196
Max Act: 5.9508. Min Act: -0.1700
Data Index: 4632891 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4196. Min Range: -6.4196
Max Act: 5.9508. Min Act: -0.1700
Data Index: 5012154 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4196. Min Range: -6.4196
Max Act: 5.9508. Min Act: -0.1700
Data Index: 6412506 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4196. Min Range: -6.4196
Max Act: 5.9508. Min Act: -0.1700
Data Index: 5733574 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4196. Min Range: -6.4196
Max Act: 5.9196. Min Act: -0.1700
Data Index: 2359813 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19