Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1836 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.8805. Min Act: -0.1700
Data Index: 3884471 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.5680. Min Act: -0.1700
Data Index: 197333 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.6305. Min Act: -0.1700
Data Index: 2803138 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.5993. Min Act: -0.1700
Data Index: 3103700 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.5368. Min Act: -0.1700
Data Index: 184809 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.5368. Min Act: -0.1700
Data Index: 5737681 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.4430. Min Act: -0.1700
Data Index: 4433317 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.4118. Min Act: -0.1700
Data Index: 4978901 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.3805. Min Act: -0.1700
Data Index: 6796625 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.4118. Min Act: -0.1700
Data Index: 5392210 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.4118. Min Act: -0.1700
Data Index: 7659781 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.3805. Min Act: -0.1700
Data Index: 7036489 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.3805. Min Act: -0.1700
Data Index: 8697662 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.3180. Min Act: -0.1700
Data Index: 906204 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.2868. Min Act: -0.1700
Data Index: 4459632 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.2868. Min Act: -0.1700
Data Index: 1936885 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.2868. Min Act: -0.1700
Data Index: 8312317 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.2868. Min Act: -0.1700
Data Index: 8378703 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.2243. Min Act: -0.1700
Data Index: 8282673 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8805. Min Range: -4.8805
Max Act: 4.1930. Min Act: -0.1700
Data Index: 4043178 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19