Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2819 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.5515. Min Act: -0.1700
Data Index: 4247013 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.5515. Min Act: -0.1700
Data Index: 6987860 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.4890. Min Act: -0.1700
Data Index: 648473 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.4578. Min Act: -0.1700
Data Index: 1303200 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.3640. Min Act: -0.1700
Data Index: 1477512 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.3328. Min Act: -0.1700
Data Index: 3336675 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.3328. Min Act: -0.1700
Data Index: 6578540 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.3015. Min Act: -0.1700
Data Index: 3606557 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.2703. Min Act: -0.1700
Data Index: 8696303 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.3015. Min Act: -0.1700
Data Index: 8733376 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.2703. Min Act: -0.1700
Data Index: 3340825 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.2390. Min Act: -0.1700
Data Index: 5470965 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.2390. Min Act: -0.1700
Data Index: 7620551 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.2390. Min Act: -0.1700
Data Index: 2591570 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.2078. Min Act: -0.1700
Data Index: 7984095 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.2078. Min Act: -0.1700
Data Index: 2377718 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.2078. Min Act: -0.1700
Data Index: 4141754 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.2078. Min Act: -0.1700
Data Index: 584730 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.1453. Min Act: -0.1700
Data Index: 7501283 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5515. Min Range: -6.5515
Max Act: 6.1765. Min Act: -0.1700
Data Index: 6596029 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19