Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 173 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0523. Min Act: -0.0003

Data Index: 1641725 (Python Code)

Max Activating Token Index: 2

Text #1

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0489. Min Act: -0.0003

Data Index: 765223 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1317671 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0407. Min Act: -0.0003

Data Index: 35425 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1018005 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0404. Min Act: -0.0004

Data Index: 219904 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0400. Min Act: -0.0003

Data Index: 633935 (C4 (Web Text))

Max Activating Token Index: 291

Text #7

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0392. Min Act: -0.0003

Data Index: 1595659 (Python Code)

Max Activating Token Index: 32

Text #8

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1587603 (Python Code)

Max Activating Token Index: 306

Text #9

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0382. Min Act: -0.0003

Data Index: 259418 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0395. Min Act: -0.0003

Data Index: 736637 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0372. Min Act: -0.0003

Data Index: 391988 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0387. Min Act: -0.0003

Data Index: 1046854 (C4 (Web Text))

Max Activating Token Index: 902

Text #13

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0326. Min Act: -0.0003

Data Index: 756063 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0364. Min Act: -0.0003

Data Index: 258994 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1533839 (Python Code)

Max Activating Token Index: 126

Text #16

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1157884 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0378. Min Act: -0.0003

Data Index: 190520 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1319205 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.0523. Min Range: -0.0523

Max Act: 0.0380. Min Act: -0.0003

Data Index: 1020272 (C4 (Web Text))

Max Activating Token Index: 916