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

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

Neuron 3189 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: 0.0651. Min Range: -0.0651

Max Act: 0.0643. Min Act: -0.0002

Data Index: 93950 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0651. Min Act: -0.0002

Data Index: 679265 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1224824 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1153839 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0490. Min Act: -0.0002

Data Index: 31091 (C4 (Web Text))

Max Activating Token Index: 315

Text #5

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0406. Min Act: -0.0002

Data Index: 135376 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0418. Min Act: -0.0002

Data Index: 621127 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0358. Min Act: -0.0002

Data Index: 367035 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1049281 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0353. Min Act: -0.0002

Data Index: 545100 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0370. Min Act: -0.0002

Data Index: 303335 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1227765 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0364. Min Act: -0.0002

Data Index: 971532 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0362. Min Act: -0.0002

Data Index: 424 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1133091 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0361. Min Act: -0.0002

Data Index: 911237 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0343. Min Act: -0.0002

Data Index: 158195 (C4 (Web Text))

Max Activating Token Index: 762

Text #17

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0335. Min Act: -0.0002

Data Index: 920767 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0339. Min Act: -0.0002

Data Index: 259611 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 0.0651. Min Range: -0.0651

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1154081 (C4 (Web Text))

Max Activating Token Index: 148