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

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

Neuron 832 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1221. Min Act: -0.0002

Data Index: 1441430 (Python Code)

Max Activating Token Index: 68

Text #1

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1216. Min Act: -0.0002

Data Index: 455506 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1203596 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1124. Min Act: -0.0002

Data Index: 959298 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1103. Min Act: -0.0002

Data Index: 621301 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1096. Min Act: -0.0002

Data Index: 430962 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1043. Min Act: -0.0002

Data Index: 732045 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1047. Min Act: -0.0002

Data Index: 807697 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1048. Min Act: -0.0002

Data Index: 913438 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.1042. Min Act: -0.0002

Data Index: 124494 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0985. Min Act: -0.0002

Data Index: 671327 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0972. Min Act: -0.0002

Data Index: 99879 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0945. Min Act: -0.0002

Data Index: 1043587 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0961. Min Act: -0.0002

Data Index: 359432 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0941. Min Act: -0.0002

Data Index: 258641 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0958. Min Act: -0.0002

Data Index: 1456691 (Python Code)

Max Activating Token Index: 415

Text #16

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1255216 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0947. Min Act: -0.0002

Data Index: 923492 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1341581 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.1221. Min Range: -0.1221

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1629861 (Python Code)

Max Activating Token Index: 246