Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2830 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5738. Min Range: -7.5738
Max Act: 7.5738. Min Act: -0.1700
Data Index: 3381267 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5738. Min Range: -7.5738
Max Act: 7.1988. Min Act: -0.1700
Data Index: 7463919 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5738. Min Range: -7.5738
Max Act: 7.0738. Min Act: -0.1700
Data Index: 5030488 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5738. Min Range: -7.5738
Max Act: 7.0738. Min Act: -0.1700
Data Index: 4640528 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5738. Min Range: -7.5738
Max Act: 7.0426. Min Act: -0.1700
Data Index: 1420331 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5738. Min Range: -7.5738
Max Act: 7.0426. Min Act: -0.1700
Data Index: 174737 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5738. Min Range: -7.5738
Max Act: 6.9801. Min Act: -0.1700
Data Index: 8304571 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5738. Min Range: -7.5738
Max Act: 6.9801. Min Act: -0.1700
Data Index: 4872547 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5738. Min Range: -7.5738
Max Act: 6.8863. Min Act: -0.1700
Data Index: 3265682 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5738. Min Range: -7.5738
Max Act: 6.8863. Min Act: -0.1700
Data Index: 6674081 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5738. Min Range: -7.5738
Max Act: 6.8238. Min Act: -0.1700
Data Index: 5354655 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5738. Min Range: -7.5738
Max Act: 6.8238. Min Act: -0.1700
Data Index: 8262617 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5738. Min Range: -7.5738
Max Act: 6.7926. Min Act: -0.1700
Data Index: 8064457 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5738. Min Range: -7.5738
Max Act: 6.7613. Min Act: -0.1700
Data Index: 3957899 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5738. Min Range: -7.5738
Max Act: 6.7301. Min Act: -0.1700
Data Index: 4543074 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5738. Min Range: -7.5738
Max Act: 6.6988. Min Act: -0.1700
Data Index: 3788226 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5738. Min Range: -7.5738
Max Act: 6.7301. Min Act: -0.1700
Data Index: 122118 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5738. Min Range: -7.5738
Max Act: 6.7301. Min Act: -0.1700
Data Index: 1027066 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5738. Min Range: -7.5738
Max Act: 6.7301. Min Act: -0.1700
Data Index: 4979319 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5738. Min Range: -7.5738
Max Act: 6.6988. Min Act: -0.1700
Data Index: 2214643 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19