Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 644 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.2995. Min Act: -0.1700
Data Index: 2027523 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full textTruncated
Full Text #0
Text #1
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.1513. Min Act: -0.1700
Data Index: 8652135 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full textTruncated
Full Text #1
Text #2
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.1450. Min Act: -0.1700
Data Index: 1296251 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full textTruncated
Full Text #2
Text #3
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.1336. Min Act: -0.1700
Data Index: 4662016 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full textTruncated
Full Text #3
Text #4
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.0998. Min Act: -0.1700
Data Index: 2465785 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full textTruncated
Full Text #4
Text #5
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.1235. Min Act: -0.1700
Data Index: 5355737 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full textTruncated
Full Text #5
Text #6
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.1097. Min Act: -0.1700
Data Index: 8548681 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full textTruncated
Full Text #6
Text #7
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.0859. Min Act: -0.1700
Data Index: 4010991 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full textTruncated
Full Text #7
Text #8
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.1619. Min Act: -0.1700
Data Index: 1753361 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full textTruncated
Full Text #8
Text #9
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.1123. Min Act: -0.1700
Data Index: 5172165 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full textTruncated
Full Text #9
Text #10
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.0994. Min Act: -0.1700
Data Index: 2842681 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full textTruncated
Full Text #10
Text #11
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.0857. Min Act: -0.1700
Data Index: 756408 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full textTruncated
Full Text #11
Text #12
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.0800. Min Act: -0.1700
Data Index: 8505087 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full textTruncated
Full Text #12
Text #13
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.0494. Min Act: -0.1700
Data Index: 3290693 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full textTruncated
Full Text #13
Text #14
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.0696. Min Act: -0.1700
Data Index: 8654100 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full textTruncated
Full Text #14
Text #15
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.0603. Min Act: -0.1700
Data Index: 786870 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full textTruncated
Full Text #15
Text #16
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.0643. Min Act: -0.1700
Data Index: 5172160 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full textTruncated
Full Text #16
Text #17
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.0924. Min Act: -0.1700
Data Index: 2522133 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full textTruncated
Full Text #17
Text #18
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.0604. Min Act: -0.1700
Data Index: 3828049 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full textTruncated
Full Text #18
Text #19
Max Range: 3.2995. Min Range: -3.2995
Max Act: 3.0485. Min Act: -0.1700
Data Index: 6833004 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full textTruncated
Full Text #19