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

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

Neuron 4593 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5015. Min Range: -1.5015

Max Act: 1.5015. Min Act: -0.0002

Data Index: 276670 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 1.5015. Min Range: -1.5015

Max Act: 1.2835. Min Act: -0.0002

Data Index: 336794 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 1.5015. Min Range: -1.5015

Max Act: 1.2681. Min Act: -0.0002

Data Index: 471897 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 1.5015. Min Range: -1.5015

Max Act: 1.2848. Min Act: -0.0002

Data Index: 798518 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 1.5015. Min Range: -1.5015

Max Act: 1.2422. Min Act: -0.0002

Data Index: 1095354 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 1.5015. Min Range: -1.5015

Max Act: 1.2484. Min Act: -0.0002

Data Index: 745444 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 1.5015. Min Range: -1.5015

Max Act: 1.1369. Min Act: -0.0002

Data Index: 1266697 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 1.5015. Min Range: -1.5015

Max Act: 1.0856. Min Act: -0.0002

Data Index: 795678 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 1.5015. Min Range: -1.5015

Max Act: 1.0660. Min Act: -0.0002

Data Index: 682859 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 1.5015. Min Range: -1.5015

Max Act: 1.0353. Min Act: -0.0002

Data Index: 987450 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 1.5015. Min Range: -1.5015

Max Act: 1.0095. Min Act: -0.0002

Data Index: 325357 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 1.5015. Min Range: -1.5015

Max Act: 0.9918. Min Act: -0.0002

Data Index: 1223571 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 1.5015. Min Range: -1.5015

Max Act: 0.9565. Min Act: -0.0002

Data Index: 430404 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 1.5015. Min Range: -1.5015

Max Act: 1.0493. Min Act: -0.0002

Data Index: 1620895 (Python Code)

Max Activating Token Index: 411

Text #14

Max Range: 1.5015. Min Range: -1.5015

Max Act: 1.1053. Min Act: -0.0002

Data Index: 558095 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 1.5015. Min Range: -1.5015

Max Act: 1.0442. Min Act: -0.0002

Data Index: 586989 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 1.5015. Min Range: -1.5015

Max Act: 1.0148. Min Act: -0.0002

Data Index: 1505736 (Python Code)

Max Activating Token Index: 791

Text #17

Max Range: 1.5015. Min Range: -1.5015

Max Act: 1.1235. Min Act: -0.0002

Data Index: 932891 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 1.5015. Min Range: -1.5015

Max Act: 1.0360. Min Act: -0.0002

Data Index: 496629 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 1.5015. Min Range: -1.5015

Max Act: 1.0623. Min Act: -0.0002

Data Index: 1296612 (C4 (Web Text))

Max Activating Token Index: 787