Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4033 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2299. Min Range: -4.2299
Max Act: 4.2299. Min Act: -0.1700
Data Index: 2227284 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.9799. Min Act: -0.1700
Data Index: 3896734 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2299. Min Range: -4.2299
Max Act: 4.0111. Min Act: -0.1700
Data Index: 2897008 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.9799. Min Act: -0.1700
Data Index: 666013 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.9799. Min Act: -0.1700
Data Index: 1284300 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.9486. Min Act: -0.1700
Data Index: 4112460 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.9486. Min Act: -0.1700
Data Index: 3892817 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.9486. Min Act: -0.1700
Data Index: 8193356 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.9486. Min Act: -0.1700
Data Index: 4278611 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.9486. Min Act: -0.1700
Data Index: 7513223 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.9173. Min Act: -0.1700
Data Index: 4052007 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.8861. Min Act: -0.1700
Data Index: 1552693 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.8548. Min Act: -0.1700
Data Index: 6971034 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.8861. Min Act: -0.1700
Data Index: 866284 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.8548. Min Act: -0.1700
Data Index: 4153076 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.8861. Min Act: -0.1700
Data Index: 2581895 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.8548. Min Act: -0.1700
Data Index: 3233577 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.7923. Min Act: -0.1700
Data Index: 747298 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.8235. Min Act: -0.1700
Data Index: 5198760 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2299. Min Range: -4.2299
Max Act: 3.8235. Min Act: -0.1700
Data Index: 2731017 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19