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

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

Neuron 2480 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: 1.3067. Min Range: -1.3067

Max Act: 1.2480. Min Act: -0.0002

Data Index: 1271169 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.3067. Min Act: -0.0001

Data Index: 223681 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.1845. Min Act: -0.0002

Data Index: 296430 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.1117. Min Act: -0.0001

Data Index: 538190 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.1147. Min Act: -0.0001

Data Index: 1072464 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.1634. Min Act: -0.0001

Data Index: 90863 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.1866. Min Act: -0.0002

Data Index: 755998 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.1142. Min Act: -0.0001

Data Index: 337582 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.0926. Min Act: -0.0001

Data Index: 330297 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.0955. Min Act: -0.0002

Data Index: 317626 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.0960. Min Act: -0.0002

Data Index: 429369 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.1502. Min Act: -0.0002

Data Index: 513985 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.1030. Min Act: -0.0001

Data Index: 1083070 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.9591. Min Act: -0.0001

Data Index: 68316 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.1194. Min Act: -0.0002

Data Index: 284418 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.1248. Min Act: -0.0001

Data Index: 851207 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.0168. Min Act: -0.0001

Data Index: 6766 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.0803. Min Act: -0.0001

Data Index: 379551 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.0434. Min Act: -0.0001

Data Index: 1111995 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.1059. Min Act: -0.0002

Data Index: 539585 (C4 (Web Text))

Max Activating Token Index: 678