Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 920 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.6022. Min Act: -0.1700
Data Index: 4815553 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.5377. Min Act: -0.1700
Data Index: 115231 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.5216. Min Act: -0.1700
Data Index: 7670407 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.5054. Min Act: -0.1700
Data Index: 494118 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.4729. Min Act: -0.1700
Data Index: 115233 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.4892. Min Act: -0.1700
Data Index: 5139774 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.4567. Min Act: -0.1700
Data Index: 1150959 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.4567. Min Act: -0.1700
Data Index: 115232 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.4567. Min Act: -0.1700
Data Index: 7443399 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.4404. Min Act: -0.1700
Data Index: 4773885 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.4242. Min Act: -0.1700
Data Index: 8458545 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.4242. Min Act: -0.1700
Data Index: 678860 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.4242. Min Act: -0.1700
Data Index: 2561848 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.4242. Min Act: -0.1700
Data Index: 2759114 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.3752. Min Act: -0.1700
Data Index: 5083243 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.4242. Min Act: -0.1700
Data Index: 7123868 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.4079. Min Act: -0.1700
Data Index: 3773873 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.4242. Min Act: -0.1700
Data Index: 115234 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.4079. Min Act: -0.1700
Data Index: 5676655 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6022. Min Range: -2.6022
Max Act: 2.3915. Min Act: -0.1700
Data Index: 5220257 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19