Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3186 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0948. Min Range: -6.0948
Max Act: 6.0948. Min Act: -0.1700
Data Index: 4509570 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0948. Min Range: -6.0948
Max Act: 5.8448. Min Act: -0.1700
Data Index: 5541738 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0948. Min Range: -6.0948
Max Act: 5.8136. Min Act: -0.1700
Data Index: 1768568 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0948. Min Range: -6.0948
Max Act: 5.7823. Min Act: -0.1700
Data Index: 5213940 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0948. Min Range: -6.0948
Max Act: 5.7823. Min Act: -0.1700
Data Index: 6270088 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0948. Min Range: -6.0948
Max Act: 5.7511. Min Act: -0.1700
Data Index: 5943 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0948. Min Range: -6.0948
Max Act: 5.7511. Min Act: -0.1700
Data Index: 4809928 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0948. Min Range: -6.0948
Max Act: 5.7198. Min Act: -0.1700
Data Index: 8134663 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0948. Min Range: -6.0948
Max Act: 5.7198. Min Act: -0.1700
Data Index: 2053107 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0948. Min Range: -6.0948
Max Act: 5.7198. Min Act: -0.1700
Data Index: 5873093 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0948. Min Range: -6.0948
Max Act: 5.7198. Min Act: -0.1700
Data Index: 5205316 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0948. Min Range: -6.0948
Max Act: 5.7198. Min Act: -0.1700
Data Index: 550244 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0948. Min Range: -6.0948
Max Act: 5.6886. Min Act: -0.1700
Data Index: 937071 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0948. Min Range: -6.0948
Max Act: 5.6886. Min Act: -0.1700
Data Index: 6594509 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0948. Min Range: -6.0948
Max Act: 5.6886. Min Act: -0.1698
Data Index: 8105475 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0948. Min Range: -6.0948
Max Act: 5.6573. Min Act: -0.1700
Data Index: 714759 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0948. Min Range: -6.0948
Max Act: 5.6573. Min Act: -0.1700
Data Index: 3538669 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0948. Min Range: -6.0948
Max Act: 5.6573. Min Act: -0.1700
Data Index: 2384327 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0948. Min Range: -6.0948
Max Act: 5.6573. Min Act: -0.1700
Data Index: 308711 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0948. Min Range: -6.0948
Max Act: 5.6573. Min Act: -0.1700
Data Index: 5744024 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19