Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2189 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0571. Min Act: -0.0002

Data Index: 409989 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0492. Min Act: -0.0002

Data Index: 818350 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0465. Min Act: -0.0002

Data Index: 883872 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0450. Min Act: -0.0002

Data Index: 361731 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1079862 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1434129 (Python Code)

Max Activating Token Index: 4

Text #6

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0418. Min Act: -0.0002

Data Index: 659386 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1034772 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0413. Min Act: -0.0002

Data Index: 995648 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1465297 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0380. Min Act: -0.0002

Data Index: 1556053 (Python Code)

Max Activating Token Index: 420

Text #11

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1458628 (Python Code)

Max Activating Token Index: 91

Text #12

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0381. Min Act: -0.0002

Data Index: 1150612 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1498821 (Python Code)

Max Activating Token Index: 14

Text #14

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1615766 (Python Code)

Max Activating Token Index: 196

Text #15

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1450581 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1431139 (Python Code)

Max Activating Token Index: 202

Text #17

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0361. Min Act: -0.0002

Data Index: 1458857 (Python Code)

Max Activating Token Index: 64

Text #18

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1437205 (Python Code)

Max Activating Token Index: 3

Text #19

Max Range: 0.0571. Min Range: -0.0571

Max Act: 0.0337. Min Act: -0.0002

Data Index: 792006 (C4 (Web Text))

Max Activating Token Index: 294