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

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

Neuron 1300 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: 0.0424. Min Range: -0.0424

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1248460 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0411. Min Act: -0.0004

Data Index: 478684 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0409. Min Act: -0.0003

Data Index: 446942 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0379. Min Act: -0.0003

Data Index: 535532 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0424. Min Act: -0.0003

Data Index: 530588 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0403. Min Act: -0.0003

Data Index: 80424 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0423. Min Act: -0.0003

Data Index: 488971 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0406. Min Act: -0.0003

Data Index: 134301 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0382. Min Act: -0.0003

Data Index: 873099 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0401. Min Act: -0.0003

Data Index: 602713 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0413. Min Act: -0.0003

Data Index: 636383 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0383. Min Act: -0.0003

Data Index: 556508 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0415. Min Act: -0.0004

Data Index: 401642 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0395. Min Act: -0.0003

Data Index: 523280 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0378. Min Act: -0.0003

Data Index: 932194 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0397. Min Act: -0.0003

Data Index: 110735 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0405. Min Act: -0.0003

Data Index: 202843 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0387. Min Act: -0.0003

Data Index: 800207 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0378. Min Act: -0.0004

Data Index: 228479 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0390. Min Act: -0.0003

Data Index: 230492 (C4 (Web Text))

Max Activating Token Index: 718