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

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

Neuron 2535 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1712. Min Act: -0.0000

Data Index: 312459 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1301. Min Act: -0.0000

Data Index: 640962 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1372. Min Act: -0.0000

Data Index: 7547 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1105. Min Act: -0.0000

Data Index: 119556 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1321. Min Act: -0.0000

Data Index: 2541 (C4 (Web Text))

Max Activating Token Index: 926

Text #5

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1053. Min Act: -0.0000

Data Index: 588248 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1131. Min Act: -0.0000

Data Index: 1310885 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1089. Min Act: -0.0000

Data Index: 691527 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1212705 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0980. Min Act: -0.0000

Data Index: 186287 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1042526 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1022. Min Act: -0.0000

Data Index: 997024 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1027. Min Act: -0.0000

Data Index: 283036 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0928. Min Act: -0.0000

Data Index: 1099923 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0884. Min Act: -0.0000

Data Index: 886022 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0771. Min Act: -0.0000

Data Index: 509922 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1133. Min Act: -0.0000

Data Index: 1264044 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0884. Min Act: -0.0000

Data Index: 350120 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0811. Min Act: -0.0000

Data Index: 246168 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0989. Min Act: -0.0000

Data Index: 967881 (C4 (Web Text))

Max Activating Token Index: 489