Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2975 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4155. Min Range: -6.4155
Max Act: 6.4155. Min Act: -0.1700
Data Index: 1707342 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4155. Min Range: -6.4155
Max Act: 6.2905. Min Act: -0.1700
Data Index: 5415668 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4155. Min Range: -6.4155
Max Act: 6.2592. Min Act: -0.1700
Data Index: 5427505 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4155. Min Range: -6.4155
Max Act: 6.1342. Min Act: -0.1700
Data Index: 2630389 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4155. Min Range: -6.4155
Max Act: 6.1030. Min Act: -0.1700
Data Index: 5438575 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4155. Min Range: -6.4155
Max Act: 5.9780. Min Act: -0.1700
Data Index: 656579 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4155. Min Range: -6.4155
Max Act: 5.8842. Min Act: -0.1700
Data Index: 7981929 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4155. Min Range: -6.4155
Max Act: 5.8530. Min Act: -0.1700
Data Index: 4561255 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4155. Min Range: -6.4155
Max Act: 5.7592. Min Act: -0.1700
Data Index: 100372 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4155. Min Range: -6.4155
Max Act: 5.7905. Min Act: -0.1700
Data Index: 323853 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4155. Min Range: -6.4155
Max Act: 5.7280. Min Act: -0.1700
Data Index: 1733484 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4155. Min Range: -6.4155
Max Act: 5.7905. Min Act: -0.1700
Data Index: 1163935 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4155. Min Range: -6.4155
Max Act: 5.7592. Min Act: -0.1700
Data Index: 3332022 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4155. Min Range: -6.4155
Max Act: 5.7280. Min Act: -0.1700
Data Index: 4282189 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4155. Min Range: -6.4155
Max Act: 5.7280. Min Act: -0.1700
Data Index: 5872656 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4155. Min Range: -6.4155
Max Act: 5.6967. Min Act: -0.1700
Data Index: 3502048 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4155. Min Range: -6.4155
Max Act: 5.6967. Min Act: -0.1700
Data Index: 1128992 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4155. Min Range: -6.4155
Max Act: 5.6655. Min Act: -0.1700
Data Index: 4131334 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4155. Min Range: -6.4155
Max Act: 5.6967. Min Act: -0.1700
Data Index: 1509961 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4155. Min Range: -6.4155
Max Act: 5.6655. Min Act: -0.1700
Data Index: 3344941 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19