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

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

Neuron 4222 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: 0.0560. Min Range: -0.0560

Max Act: 0.0493. Min Act: -0.0002

Data Index: 236443 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0560. Min Act: -0.0002

Data Index: 527697 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0532. Min Act: -0.0002

Data Index: 615973 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1209085 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1351489 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0476. Min Act: -0.0002

Data Index: 396372 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0506. Min Act: -0.0002

Data Index: 600995 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1208803 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0451. Min Act: -0.0002

Data Index: 649783 (C4 (Web Text))

Max Activating Token Index: 385

Text #9

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1214771 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0402. Min Act: -0.0002

Data Index: 936888 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1266151 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0422. Min Act: -0.0002

Data Index: 131506 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0437. Min Act: -0.0002

Data Index: 534419 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0432. Min Act: -0.0002

Data Index: 554323 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0456. Min Act: -0.0002

Data Index: 952468 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0420. Min Act: -0.0002

Data Index: 419439 (C4 (Web Text))

Max Activating Token Index: 501

Text #17

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0442. Min Act: -0.0002

Data Index: 110590 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0380. Min Act: -0.0002

Data Index: 1111987 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1225248 (C4 (Web Text))

Max Activating Token Index: 25