Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3395 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4546. Min Range: -4.4546
Max Act: 4.4546. Min Act: -0.1700
Data Index: 7044345 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4546. Min Range: -4.4546
Max Act: 4.3296. Min Act: -0.1700
Data Index: 1308619 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4546. Min Range: -4.4546
Max Act: 4.2984. Min Act: -0.1700
Data Index: 7498971 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4546. Min Range: -4.4546
Max Act: 4.2984. Min Act: -0.1700
Data Index: 6405489 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4546. Min Range: -4.4546
Max Act: 4.1734. Min Act: -0.1700
Data Index: 4981884 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4546. Min Range: -4.4546
Max Act: 4.1421. Min Act: -0.1700
Data Index: 6381344 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4546. Min Range: -4.4546
Max Act: 4.1421. Min Act: -0.1700
Data Index: 7228343 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4546. Min Range: -4.4546
Max Act: 4.1108. Min Act: -0.1700
Data Index: 5964010 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4546. Min Range: -4.4546
Max Act: 4.1108. Min Act: -0.1700
Data Index: 8653208 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4546. Min Range: -4.4546
Max Act: 4.0796. Min Act: -0.1700
Data Index: 3587004 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4546. Min Range: -4.4546
Max Act: 4.0483. Min Act: -0.1700
Data Index: 2854241 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4546. Min Range: -4.4546
Max Act: 4.0171. Min Act: -0.1700
Data Index: 2422940 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4546. Min Range: -4.4546
Max Act: 4.0171. Min Act: -0.1700
Data Index: 8671875 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4546. Min Range: -4.4546
Max Act: 4.0483. Min Act: -0.1700
Data Index: 6717914 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4546. Min Range: -4.4546
Max Act: 4.0171. Min Act: -0.1700
Data Index: 117095 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4546. Min Range: -4.4546
Max Act: 4.0171. Min Act: -0.1700
Data Index: 4727250 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4546. Min Range: -4.4546
Max Act: 3.9858. Min Act: -0.1700
Data Index: 6526128 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4546. Min Range: -4.4546
Max Act: 4.0171. Min Act: -0.1700
Data Index: 6556836 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4546. Min Range: -4.4546
Max Act: 4.0171. Min Act: -0.1700
Data Index: 6689435 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4546. Min Range: -4.4546
Max Act: 4.0171. Min Act: -0.1700
Data Index: 3488100 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19