Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1050 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.2043. Min Act: -0.0001

Data Index: 424615 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.1709. Min Act: -0.0001

Data Index: 694074 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.1598. Min Act: -0.0002

Data Index: 479825 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.1569. Min Act: -0.0001

Data Index: 445355 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.1605. Min Act: -0.0002

Data Index: 1075323 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.1627. Min Act: -0.0001

Data Index: 1159739 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.1483. Min Act: -0.0001

Data Index: 1196185 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.1472. Min Act: -0.0002

Data Index: 680750 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.1457. Min Act: -0.0001

Data Index: 578358 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.1427. Min Act: -0.0002

Data Index: 1119462 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.1380. Min Act: -0.0002

Data Index: 842302 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.1425. Min Act: -0.0002

Data Index: 1009778 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.1404. Min Act: -0.0002

Data Index: 1349889 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.1350. Min Act: -0.0002

Data Index: 726758 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.1353. Min Act: -0.0002

Data Index: 532840 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.1423. Min Act: -0.0002

Data Index: 398300 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.1375. Min Act: -0.0002

Data Index: 446258 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.1323. Min Act: -0.0002

Data Index: 483405 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.1284. Min Act: -0.0002

Data Index: 1172045 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.2043. Min Range: -0.2043

Max Act: 0.1376. Min Act: -0.0002

Data Index: 982844 (C4 (Web Text))

Max Activating Token Index: 864