Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1403 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0691. Min Range: -7.0691
Max Act: 7.0691. Min Act: -0.1700
Data Index: 6804349 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.9128. Min Act: -0.1700
Data Index: 4250302 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.6003. Min Act: -0.1700
Data Index: 4645746 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.1941. Min Act: -0.1700
Data Index: 1991119 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.4441. Min Act: -0.1700
Data Index: 1875322 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.0378. Min Act: -0.1700
Data Index: 1799561 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.4753. Min Act: -0.1700
Data Index: 1247882 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.1003. Min Act: -0.1700
Data Index: 5312935 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.3503. Min Act: -0.1700
Data Index: 5490514 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.2253. Min Act: -0.1700
Data Index: 8595602 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.0066. Min Act: -0.1700
Data Index: 952850 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0691. Min Range: -7.0691
Max Act: 5.9753. Min Act: -0.1700
Data Index: 5235381 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.2253. Min Act: -0.1700
Data Index: 1139889 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.3816. Min Act: -0.1700
Data Index: 5817582 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.2253. Min Act: -0.1700
Data Index: 2790380 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.2878. Min Act: -0.1700
Data Index: 8744709 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.1316. Min Act: -0.1700
Data Index: 7558824 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.1628. Min Act: -0.1700
Data Index: 7208651 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.1316. Min Act: -0.1700
Data Index: 8711300 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0691. Min Range: -7.0691
Max Act: 6.1628. Min Act: -0.1700
Data Index: 6099170 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19