Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4621 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1605. Min Act: -0.0001

Data Index: 134956 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1305. Min Act: -0.0001

Data Index: 942484 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0648. Min Act: -0.0001

Data Index: 294545 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0995. Min Act: -0.0001

Data Index: 148998 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1500552 (Python Code)

Max Activating Token Index: 841

Text #5

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0534. Min Act: -0.0001

Data Index: 1015893 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1096758 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0472. Min Act: -0.0001

Data Index: 1056511 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0434. Min Act: -0.0001

Data Index: 30074 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0486. Min Act: -0.0001

Data Index: 745085 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0440. Min Act: -0.0001

Data Index: 426247 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1119601 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0377. Min Act: -0.0001

Data Index: 1540841 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0415. Min Act: -0.0001

Data Index: 1522001 (Python Code)

Max Activating Token Index: 863

Text #14

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0431. Min Act: -0.0001

Data Index: 517271 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0408. Min Act: -0.0001

Data Index: 377871 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0412. Min Act: -0.0001

Data Index: 1133973 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0423. Min Act: -0.0001

Data Index: 1420832 (Python Code)

Max Activating Token Index: 1020

Text #18

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1107225 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.0378. Min Act: -0.0001

Data Index: 172178 (C4 (Web Text))

Max Activating Token Index: 626