Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4194 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.5765. Min Act: -0.1700
Data Index: 6152808 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.5453. Min Act: -0.1700
Data Index: 6747318 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.4515. Min Act: -0.1700
Data Index: 6756741 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.4828. Min Act: -0.1700
Data Index: 5889066 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.4828. Min Act: -0.1700
Data Index: 500677 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.4828. Min Act: -0.1700
Data Index: 1392888 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.4515. Min Act: -0.1700
Data Index: 5764658 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.4203. Min Act: -0.1700
Data Index: 6869621 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.3890. Min Act: -0.1700
Data Index: 6538536 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.3578. Min Act: -0.1700
Data Index: 5234848 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.3578. Min Act: -0.1700
Data Index: 1785804 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.2953. Min Act: -0.1700
Data Index: 6788047 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.2640. Min Act: -0.1700
Data Index: 4201321 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.2640. Min Act: -0.1700
Data Index: 5220262 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.2640. Min Act: -0.1700
Data Index: 2764592 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.2640. Min Act: -0.1700
Data Index: 73751 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.2328. Min Act: -0.1700
Data Index: 229593 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.2328. Min Act: -0.1700
Data Index: 2386074 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.2640. Min Act: -0.1700
Data Index: 1237824 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5765. Min Range: -6.5765
Max Act: 6.2328. Min Act: -0.1700
Data Index: 4114083 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19