Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2992 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.7733. Min Act: -0.1700
Data Index: 6670077 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.5229. Min Act: -0.1700
Data Index: 8095915 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.4603. Min Act: -0.1700
Data Index: 8647894 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.4133. Min Act: -0.1700
Data Index: 3444570 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.3662. Min Act: -0.1700
Data Index: 6496833 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.3348. Min Act: -0.1700
Data Index: 1813788 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.3976. Min Act: -0.1700
Data Index: 4111974 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.3034. Min Act: -0.1700
Data Index: 5033800 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.2877. Min Act: -0.1700
Data Index: 5809102 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.2720. Min Act: -0.1700
Data Index: 3817607 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.2563. Min Act: -0.1700
Data Index: 4016003 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.2720. Min Act: -0.1700
Data Index: 1342887 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.1935. Min Act: -0.1700
Data Index: 7856086 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.2092. Min Act: -0.1700
Data Index: 8202914 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.2249. Min Act: -0.1700
Data Index: 8015621 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.2720. Min Act: -0.1700
Data Index: 2525967 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.2092. Min Act: -0.1700
Data Index: 6621258 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.2406. Min Act: -0.1700
Data Index: 3260940 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.2249. Min Act: -0.1700
Data Index: 730974 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7733. Min Range: -3.7733
Max Act: 3.2092. Min Act: -0.1700
Data Index: 123570 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19