Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1959 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0639. Min Act: -0.0002

Data Index: 439133 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1305879 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0503. Min Act: -0.0001

Data Index: 879979 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0481. Min Act: -0.0001

Data Index: 573470 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0449. Min Act: -0.0001

Data Index: 326164 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0437. Min Act: -0.0002

Data Index: 98732 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0452. Min Act: -0.0001

Data Index: 74577 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1273371 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0432. Min Act: -0.0002

Data Index: 201760 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0467. Min Act: -0.0001

Data Index: 806496 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0436. Min Act: -0.0002

Data Index: 824941 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0434. Min Act: -0.0001

Data Index: 358032 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0435. Min Act: -0.0002

Data Index: 508299 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0443. Min Act: -0.0002

Data Index: 613203 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0450. Min Act: -0.0002

Data Index: 918337 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0434. Min Act: -0.0002

Data Index: 208551 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0421. Min Act: -0.0002

Data Index: 150261 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0421. Min Act: -0.0001

Data Index: 1218880 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0416. Min Act: -0.0002

Data Index: 345275 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0424. Min Act: -0.0002

Data Index: 359153 (C4 (Web Text))

Max Activating Token Index: 822