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

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

Neuron 2221 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2272. Min Range: -1.2272

Max Act: 1.2272. Min Act: -0.0000

Data Index: 801677 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 1.2272. Min Range: -1.2272

Max Act: 1.2024. Min Act: -0.0000

Data Index: 45114 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 1.2272. Min Range: -1.2272

Max Act: 1.0937. Min Act: -0.0000

Data Index: 1014605 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 1.2272. Min Range: -1.2272

Max Act: 1.1254. Min Act: -0.0000

Data Index: 47082 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 1.2272. Min Range: -1.2272

Max Act: 1.1155. Min Act: -0.0000

Data Index: 1498340 (Python Code)

Max Activating Token Index: 325

Text #5

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.9616. Min Act: -0.0000

Data Index: 1561827 (Python Code)

Max Activating Token Index: 980

Text #6

Max Range: 1.2272. Min Range: -1.2272

Max Act: 1.0183. Min Act: -0.0000

Data Index: 344107 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.9148. Min Act: -0.0000

Data Index: 886641 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.9439. Min Act: -0.0000

Data Index: 1231744 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 1.2272. Min Range: -1.2272

Max Act: 1.0034. Min Act: -0.0001

Data Index: 18892 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.8482. Min Act: -0.0001

Data Index: 1606474 (Python Code)

Max Activating Token Index: 270

Text #11

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.9043. Min Act: -0.0000

Data Index: 1017885 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.8321. Min Act: -0.0000

Data Index: 82826 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.9294. Min Act: -0.0000

Data Index: 1343316 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.8338. Min Act: -0.0000

Data Index: 309191 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.7674. Min Act: -0.0000

Data Index: 388756 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.8565. Min Act: -0.0000

Data Index: 495687 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.8238. Min Act: -0.0000

Data Index: 41512 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.8434. Min Act: -0.0001

Data Index: 1421356 (Python Code)

Max Activating Token Index: 337

Text #19

Max Range: 1.2272. Min Range: -1.2272

Max Act: 0.8416. Min Act: -0.0000

Data Index: 487535 (C4 (Web Text))

Max Activating Token Index: 760