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

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

Neuron 325 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: 0.6416. Min Range: -0.6416

Max Act: 0.6390. Min Act: -0.0002

Data Index: 643004 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.6413. Min Act: -0.0002

Data Index: 646993 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.6376. Min Act: -0.0002

Data Index: 604728 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.6416. Min Act: -0.0002

Data Index: 728921 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.6405. Min Act: -0.0002

Data Index: 1212814 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.6308. Min Act: -0.0002

Data Index: 568671 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.6309. Min Act: -0.0002

Data Index: 354141 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.6240. Min Act: -0.0002

Data Index: 207277 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.6155. Min Act: -0.0002

Data Index: 59493 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.6134. Min Act: -0.0002

Data Index: 218778 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.6196. Min Act: -0.0002

Data Index: 966737 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.6178. Min Act: -0.0002

Data Index: 177207 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.6195. Min Act: -0.0002

Data Index: 1185250 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.6061. Min Act: -0.0002

Data Index: 717931 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.6012. Min Act: -0.0001

Data Index: 1030979 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.6027. Min Act: -0.0002

Data Index: 941052 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.5881. Min Act: -0.0002

Data Index: 991400 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.5974. Min Act: -0.0002

Data Index: 678709 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.5836. Min Act: -0.0002

Data Index: 1355005 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 0.6416. Min Range: -0.6416

Max Act: 0.5942. Min Act: -0.0002

Data Index: 197633 (C4 (Web Text))

Max Activating Token Index: 959