Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3480 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1057. Min Range: -7.1057
Max Act: 7.1057. Min Act: -0.1700
Data Index: 7489473 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1057. Min Range: -7.1057
Max Act: 6.9495. Min Act: -0.1700
Data Index: 7627736 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1057. Min Range: -7.1057
Max Act: 6.6370. Min Act: -0.1700
Data Index: 1115415 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1057. Min Range: -7.1057
Max Act: 6.6995. Min Act: -0.1700
Data Index: 4287513 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1057. Min Range: -7.1057
Max Act: 6.7307. Min Act: -0.1700
Data Index: 3588817 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1057. Min Range: -7.1057
Max Act: 6.5745. Min Act: -0.1700
Data Index: 4134848 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1057. Min Range: -7.1057
Max Act: 6.6682. Min Act: -0.1700
Data Index: 5936571 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1057. Min Range: -7.1057
Max Act: 6.6057. Min Act: -0.1700
Data Index: 4787782 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1057. Min Range: -7.1057
Max Act: 6.5745. Min Act: -0.1700
Data Index: 1115422 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1057. Min Range: -7.1057
Max Act: 6.6682. Min Act: -0.1700
Data Index: 8054120 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1057. Min Range: -7.1057
Max Act: 6.5432. Min Act: -0.1700
Data Index: 3482079 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1057. Min Range: -7.1057
Max Act: 6.5432. Min Act: -0.1700
Data Index: 5331307 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1057. Min Range: -7.1057
Max Act: 6.4807. Min Act: -0.1700
Data Index: 5046105 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1057. Min Range: -7.1057
Max Act: 6.4807. Min Act: -0.1700
Data Index: 1312547 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1057. Min Range: -7.1057
Max Act: 6.4182. Min Act: -0.1700
Data Index: 4888506 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1057. Min Range: -7.1057
Max Act: 6.4495. Min Act: -0.1700
Data Index: 2528760 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1057. Min Range: -7.1057
Max Act: 6.4495. Min Act: -0.1700
Data Index: 3706734 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1057. Min Range: -7.1057
Max Act: 6.3557. Min Act: -0.1700
Data Index: 1238445 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1057. Min Range: -7.1057
Max Act: 6.3870. Min Act: -0.1700
Data Index: 2534166 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1057. Min Range: -7.1057
Max Act: 6.3870. Min Act: -0.1700
Data Index: 1912191 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19