Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1960 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.6931. Min Act: -0.1700
Data Index: 6100029 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.5993. Min Act: -0.1700
Data Index: 5698752 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.4431. Min Act: -0.1700
Data Index: 8546793 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.4118. Min Act: -0.1700
Data Index: 1902093 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.4118. Min Act: -0.1700
Data Index: 4706100 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.3806. Min Act: -0.1700
Data Index: 6887846 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.3493. Min Act: -0.1700
Data Index: 5214841 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.3181. Min Act: -0.1700
Data Index: 5204855 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.2868. Min Act: -0.1700
Data Index: 6689395 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.2868. Min Act: -0.1700
Data Index: 51189 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.2868. Min Act: -0.1700
Data Index: 5741453 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.2868. Min Act: -0.1700
Data Index: 3247901 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.2868. Min Act: -0.1700
Data Index: 4925533 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.2556. Min Act: -0.1700
Data Index: 2565064 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.2868. Min Act: -0.1700
Data Index: 8269049 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.2556. Min Act: -0.1700
Data Index: 4265699 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.2243. Min Act: -0.1700
Data Index: 1096844 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.2243. Min Act: -0.1700
Data Index: 1560059 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.2243. Min Act: -0.1700
Data Index: 1211102 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6931. Min Range: -5.6931
Max Act: 5.2556. Min Act: -0.1700
Data Index: 5496493 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19