Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2047 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0793. Min Range: -5.0793
Max Act: 5.0793. Min Act: -0.1700
Data Index: 1467008 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0793. Min Range: -5.0793
Max Act: 4.8918. Min Act: -0.1700
Data Index: 2259225 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0793. Min Range: -5.0793
Max Act: 4.8293. Min Act: -0.1700
Data Index: 3143933 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0793. Min Range: -5.0793
Max Act: 4.7981. Min Act: -0.1700
Data Index: 5076778 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0793. Min Range: -5.0793
Max Act: 4.8293. Min Act: -0.1700
Data Index: 2813723 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0793. Min Range: -5.0793
Max Act: 4.7668. Min Act: -0.1700
Data Index: 8276763 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0793. Min Range: -5.0793
Max Act: 4.7981. Min Act: -0.1700
Data Index: 1680012 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0793. Min Range: -5.0793
Max Act: 4.7668. Min Act: -0.1700
Data Index: 1922750 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0793. Min Range: -5.0793
Max Act: 4.7668. Min Act: -0.1700
Data Index: 6461372 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0793. Min Range: -5.0793
Max Act: 4.7668. Min Act: -0.1700
Data Index: 1206136 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0793. Min Range: -5.0793
Max Act: 4.7981. Min Act: -0.1700
Data Index: 1538433 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0793. Min Range: -5.0793
Max Act: 4.7356. Min Act: -0.1700
Data Index: 4729785 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0793. Min Range: -5.0793
Max Act: 4.7356. Min Act: -0.1700
Data Index: 8108250 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0793. Min Range: -5.0793
Max Act: 4.7356. Min Act: -0.1700
Data Index: 406929 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0793. Min Range: -5.0793
Max Act: 4.7043. Min Act: -0.1700
Data Index: 6272910 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0793. Min Range: -5.0793
Max Act: 4.6731. Min Act: -0.1700
Data Index: 3472018 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0793. Min Range: -5.0793
Max Act: 4.7043. Min Act: -0.1700
Data Index: 3899987 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0793. Min Range: -5.0793
Max Act: 4.7356. Min Act: -0.1700
Data Index: 427037 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0793. Min Range: -5.0793
Max Act: 4.7043. Min Act: -0.1700
Data Index: 7914114 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0793. Min Range: -5.0793
Max Act: 4.6731. Min Act: -0.1700
Data Index: 7654912 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19