Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1175 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.7730. Min Act: -0.1700
Data Index: 1842039 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.8355. Min Act: -0.1700
Data Index: 7546667 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.8042. Min Act: -0.1700
Data Index: 4138902 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.7730. Min Act: -0.1700
Data Index: 6224696 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.7417. Min Act: -0.1700
Data Index: 3260999 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.6792. Min Act: -0.1700
Data Index: 1664007 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.6792. Min Act: -0.1700
Data Index: 506158 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.7105. Min Act: -0.1700
Data Index: 2926772 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.7105. Min Act: -0.1700
Data Index: 3742102 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.6792. Min Act: -0.1700
Data Index: 137110 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.6480. Min Act: -0.1700
Data Index: 4987069 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.6167. Min Act: -0.1700
Data Index: 6267369 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.6167. Min Act: -0.1700
Data Index: 678002 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.6167. Min Act: -0.1700
Data Index: 6546167 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.6167. Min Act: -0.1700
Data Index: 7349268 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.6167. Min Act: -0.1700
Data Index: 644565 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.6167. Min Act: -0.1700
Data Index: 586913 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.6480. Min Act: -0.1700
Data Index: 7088432 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.6167. Min Act: -0.1700
Data Index: 555437 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8355. Min Range: -5.8355
Max Act: 5.5855. Min Act: -0.1700
Data Index: 6119404 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19