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

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

Neuron 4630 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1130. Min Act: -0.0003

Data Index: 316019 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1072. Min Act: -0.0003

Data Index: 776475 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.1033. Min Act: -0.0003

Data Index: 1218084 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0840. Min Act: -0.0003

Data Index: 1050637 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0773. Min Act: -0.0003

Data Index: 212739 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0631. Min Act: -0.0003

Data Index: 1022948 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0651. Min Act: -0.0003

Data Index: 211310 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0616. Min Act: -0.0003

Data Index: 453199 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0582. Min Act: -0.0003

Data Index: 192239 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1464270 (Python Code)

Max Activating Token Index: 277

Text #10

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0514. Min Act: -0.0003

Data Index: 370715 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0514. Min Act: -0.0003

Data Index: 689900 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0510. Min Act: -0.0003

Data Index: 1310460 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0496. Min Act: -0.0003

Data Index: 1387601 (Python Code)

Max Activating Token Index: 95

Text #14

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0494. Min Act: -0.0003

Data Index: 1020514 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1379869 (Python Code)

Max Activating Token Index: 114

Text #16

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1588978 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1596264 (Python Code)

Max Activating Token Index: 135

Text #18

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0469. Min Act: -0.0003

Data Index: 815341 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.1130. Min Range: -0.1130

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1601049 (Python Code)

Max Activating Token Index: 894