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

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

Neuron 2377 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: 0.0535. Min Range: -0.0535

Max Act: 0.0535. Min Act: -0.0002

Data Index: 666134 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0521. Min Act: -0.0002

Data Index: 789079 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0477. Min Act: -0.0002

Data Index: 289448 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0457. Min Act: -0.0002

Data Index: 336496 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0454. Min Act: -0.0002

Data Index: 291558 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1146577 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0467. Min Act: -0.0002

Data Index: 228753 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0417. Min Act: -0.0002

Data Index: 508837 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0431. Min Act: -0.0002

Data Index: 12527 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0444. Min Act: -0.0002

Data Index: 186974 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0414. Min Act: -0.0002

Data Index: 565941 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0423. Min Act: -0.0002

Data Index: 1394253 (Python Code)

Max Activating Token Index: 26

Text #12

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1272996 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1508297 (Python Code)

Max Activating Token Index: 35

Text #14

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0440. Min Act: -0.0002

Data Index: 688712 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1250646 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1385175 (Python Code)

Max Activating Token Index: 131

Text #17

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0333. Min Act: -0.0002

Data Index: 234555 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0424. Min Act: -0.0002

Data Index: 881499 (C4 (Web Text))

Max Activating Token Index: 778

Text #19

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0407. Min Act: -0.0002

Data Index: 267282 (C4 (Web Text))

Max Activating Token Index: 867