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

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

Neuron 1847 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2313. Min Range: -2.2313

Max Act: 2.0044. Min Act: -0.0000

Data Index: 55312 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 2.2313. Min Range: -2.2313

Max Act: 2.2313. Min Act: -0.0000

Data Index: 440644 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 2.2313. Min Range: -2.2313

Max Act: 2.0215. Min Act: -0.0000

Data Index: 172993 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 2.2313. Min Range: -2.2313

Max Act: 1.9132. Min Act: -0.0000

Data Index: 540748 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 2.2313. Min Range: -2.2313

Max Act: 2.0042. Min Act: -0.0000

Data Index: 275632 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 2.2313. Min Range: -2.2313

Max Act: 2.1092. Min Act: -0.0000

Data Index: 59837 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 2.2313. Min Range: -2.2313

Max Act: 1.8693. Min Act: -0.0000

Data Index: 1641388 (Python Code)

Max Activating Token Index: 709

Text #7

Max Range: 2.2313. Min Range: -2.2313

Max Act: 1.8199. Min Act: -0.0000

Data Index: 1277332 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 2.2313. Min Range: -2.2313

Max Act: 2.0190. Min Act: -0.0000

Data Index: 1506537 (Python Code)

Max Activating Token Index: 461

Text #9

Max Range: 2.2313. Min Range: -2.2313

Max Act: 1.8250. Min Act: -0.0000

Data Index: 1459155 (Python Code)

Max Activating Token Index: 471

Text #10

Max Range: 2.2313. Min Range: -2.2313

Max Act: 1.8645. Min Act: -0.0000

Data Index: 611835 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 2.2313. Min Range: -2.2313

Max Act: 1.8676. Min Act: -0.0000

Data Index: 220723 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 2.2313. Min Range: -2.2313

Max Act: 1.7455. Min Act: -0.0000

Data Index: 1329384 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 2.2313. Min Range: -2.2313

Max Act: 1.8565. Min Act: -0.0000

Data Index: 1597311 (Python Code)

Max Activating Token Index: 619

Text #14

Max Range: 2.2313. Min Range: -2.2313

Max Act: 1.8102. Min Act: -0.0000

Data Index: 75029 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 2.2313. Min Range: -2.2313

Max Act: 1.8302. Min Act: -0.0000

Data Index: 650118 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 2.2313. Min Range: -2.2313

Max Act: 1.8060. Min Act: -0.0000

Data Index: 344061 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 2.2313. Min Range: -2.2313

Max Act: 1.7666. Min Act: -0.0000

Data Index: 943935 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 2.2313. Min Range: -2.2313

Max Act: 1.7652. Min Act: -0.0000

Data Index: 312983 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 2.2313. Min Range: -2.2313

Max Act: 1.6581. Min Act: -0.0000

Data Index: 1056608 (C4 (Web Text))

Max Activating Token Index: 675