Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5631 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.4748. Min Act: -0.0000

Data Index: 1221934 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.4891. Min Act: -0.0000

Data Index: 861626 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.3887. Min Act: -0.0000

Data Index: 52555 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.5408. Min Act: -0.0000

Data Index: 1170973 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.5324. Min Act: -0.0000

Data Index: 972967 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.3941. Min Act: -0.0000

Data Index: 874271 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.2998. Min Act: 0.0000

Data Index: 150604 (C4 (Web Text))

Max Activating Token Index: 936

Text #7

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.2733. Min Act: -0.0000

Data Index: 187264 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.2610. Min Act: -0.0000

Data Index: 1114831 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.3228. Min Act: -0.0000

Data Index: 1326322 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.1638. Min Act: -0.0000

Data Index: 226406 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.2246. Min Act: -0.0000

Data Index: 282447 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.2929. Min Act: -0.0000

Data Index: 1274091 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.2170. Min Act: -0.0000

Data Index: 821407 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.2827. Min Act: -0.0000

Data Index: 1218672 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.2040. Min Act: -0.0000

Data Index: 52396 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.2038. Min Act: -0.0000

Data Index: 302113 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.1892. Min Act: -0.0000

Data Index: 90692 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.1747. Min Act: -0.0000

Data Index: 975400 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 1.5408. Min Range: -1.5408

Max Act: 1.0960. Min Act: -0.0000

Data Index: 1202638 (C4 (Web Text))

Max Activating Token Index: 740