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

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

Neuron 2850 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2924. Min Range: -1.2924

Max Act: 1.2924. Min Act: -0.0000

Data Index: 814285 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 1.2924. Min Range: -1.2924

Max Act: 1.2317. Min Act: -0.0001

Data Index: 1171980 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 1.2924. Min Range: -1.2924

Max Act: 1.1654. Min Act: -0.0000

Data Index: 450181 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 1.2924. Min Range: -1.2924

Max Act: 1.2251. Min Act: -0.0000

Data Index: 1211113 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 1.2924. Min Range: -1.2924

Max Act: 1.1956. Min Act: -0.0000

Data Index: 685175 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 1.2924. Min Range: -1.2924

Max Act: 1.1085. Min Act: -0.0000

Data Index: 533930 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 1.2924. Min Range: -1.2924

Max Act: 1.1897. Min Act: -0.0001

Data Index: 980787 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 1.2924. Min Range: -1.2924

Max Act: 1.1405. Min Act: -0.0001

Data Index: 185080 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 1.2924. Min Range: -1.2924

Max Act: 1.1128. Min Act: -0.0000

Data Index: 1097931 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 1.2924. Min Range: -1.2924

Max Act: 1.0531. Min Act: -0.0000

Data Index: 701955 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 1.2924. Min Range: -1.2924

Max Act: 1.0252. Min Act: -0.0000

Data Index: 492461 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 1.2924. Min Range: -1.2924

Max Act: 1.1510. Min Act: -0.0001

Data Index: 637292 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 1.2924. Min Range: -1.2924

Max Act: 1.0354. Min Act: -0.0000

Data Index: 56175 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 1.2924. Min Range: -1.2924

Max Act: 0.9612. Min Act: -0.0000

Data Index: 1161285 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 1.2924. Min Range: -1.2924

Max Act: 0.9474. Min Act: -0.0000

Data Index: 1017612 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 1.2924. Min Range: -1.2924

Max Act: 1.0692. Min Act: -0.0000

Data Index: 1176628 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 1.2924. Min Range: -1.2924

Max Act: 0.9627. Min Act: -0.0000

Data Index: 344188 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 1.2924. Min Range: -1.2924

Max Act: 1.1167. Min Act: -0.0001

Data Index: 1146405 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 1.2924. Min Range: -1.2924

Max Act: 1.0470. Min Act: -0.0000

Data Index: 441704 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 1.2924. Min Range: -1.2924

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1356121 (C4 (Web Text))

Max Activating Token Index: 574