Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 45 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1297. Min Act: -0.0002

Data Index: 210164 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1257. Min Act: -0.0002

Data Index: 646387 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1159. Min Act: -0.0002

Data Index: 660643 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1267. Min Act: -0.0002

Data Index: 602375 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1154. Min Act: -0.0002

Data Index: 305089 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1144. Min Act: -0.0002

Data Index: 63705 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1110. Min Act: -0.0002

Data Index: 1027306 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1182. Min Act: -0.0002

Data Index: 555125 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1100. Min Act: -0.0002

Data Index: 900799 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1040. Min Act: -0.0002

Data Index: 36843 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1011. Min Act: -0.0002

Data Index: 146538 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1013. Min Act: -0.0002

Data Index: 946130 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1038. Min Act: -0.0002

Data Index: 487250 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0982. Min Act: -0.0002

Data Index: 378791 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1030. Min Act: -0.0002

Data Index: 327624 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1017. Min Act: -0.0002

Data Index: 254997 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0998. Min Act: -0.0002

Data Index: 832085 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1024. Min Act: -0.0002

Data Index: 320882 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0986. Min Act: -0.0002

Data Index: 1179697 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0951. Min Act: -0.0002

Data Index: 886195 (C4 (Web Text))

Max Activating Token Index: 255