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

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

Neuron 1718 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0409. Min Act: -0.0005

Data Index: 530526 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0424. Min Act: -0.0006

Data Index: 423161 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0423. Min Act: -0.0006

Data Index: 202874 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0411. Min Act: -0.0006

Data Index: 32736 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0419. Min Act: -0.0006

Data Index: 229606 (C4 (Web Text))

Max Activating Token Index: 792

Text #5

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0408. Min Act: -0.0006

Data Index: 1470307 (Python Code)

Max Activating Token Index: 905

Text #6

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0392. Min Act: -0.0006

Data Index: 829438 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0381. Min Act: -0.0005

Data Index: 462858 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0389. Min Act: -0.0006

Data Index: 864380 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0386. Min Act: -0.0006

Data Index: 1347142 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0382. Min Act: -0.0006

Data Index: 352909 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0372. Min Act: -0.0006

Data Index: 546236 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0377. Min Act: -0.0006

Data Index: 1278949 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0383. Min Act: -0.0006

Data Index: 1271265 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0380. Min Act: -0.0005

Data Index: 918461 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0372. Min Act: -0.0006

Data Index: 128141 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0372. Min Act: -0.0006

Data Index: 950368 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0372. Min Act: -0.0006

Data Index: 232096 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0377. Min Act: -0.0006

Data Index: 260948 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0376. Min Act: -0.0005

Data Index: 728181 (C4 (Web Text))

Max Activating Token Index: 982