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

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

Neuron 455 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.2645. Min Act: -0.0000

Data Index: 285523 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1807. Min Act: -0.0000

Data Index: 302797 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1714. Min Act: -0.0001

Data Index: 1123899 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1697. Min Act: -0.0000

Data Index: 22954 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1579. Min Act: -0.0001

Data Index: 940967 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1508. Min Act: -0.0001

Data Index: 1047135 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1446. Min Act: -0.0000

Data Index: 72137 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1296. Min Act: -0.0000

Data Index: 639594 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1302. Min Act: -0.0000

Data Index: 251414 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1319. Min Act: -0.0000

Data Index: 168280 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1307. Min Act: -0.0000

Data Index: 1228100 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1265. Min Act: -0.0001

Data Index: 485632 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1332. Min Act: -0.0000

Data Index: 1138446 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1144. Min Act: -0.0001

Data Index: 1537687 (Python Code)

Max Activating Token Index: 506

Text #14

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1125. Min Act: -0.0000

Data Index: 416480 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1143. Min Act: -0.0001

Data Index: 261148 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1112. Min Act: -0.0000

Data Index: 959422 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1454584 (Python Code)

Max Activating Token Index: 883

Text #18

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1469571 (Python Code)

Max Activating Token Index: 485

Text #19

Max Range: 0.2645. Min Range: -0.2645

Max Act: 0.1089. Min Act: -0.0000

Data Index: 600896 (C4 (Web Text))

Max Activating Token Index: 786