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

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

Neuron 4029 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5261. Min Range: -2.5261

Max Act: 2.5261. Min Act: -0.0000

Data Index: 658214 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 2.5261. Min Range: -2.5261

Max Act: 1.9301. Min Act: -0.0000

Data Index: 53260 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 2.5261. Min Range: -2.5261

Max Act: 1.9997. Min Act: -0.0000

Data Index: 840404 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 2.5261. Min Range: -2.5261

Max Act: 1.9834. Min Act: -0.0000

Data Index: 330425 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 2.5261. Min Range: -2.5261

Max Act: 1.8596. Min Act: -0.0000

Data Index: 733550 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 2.5261. Min Range: -2.5261

Max Act: 1.8609. Min Act: -0.0000

Data Index: 791087 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 2.5261. Min Range: -2.5261

Max Act: 1.9313. Min Act: -0.0000

Data Index: 439607 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 2.5261. Min Range: -2.5261

Max Act: 1.8749. Min Act: -0.0000

Data Index: 504758 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 2.5261. Min Range: -2.5261

Max Act: 1.7415. Min Act: -0.0000

Data Index: 1184657 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 2.5261. Min Range: -2.5261

Max Act: 1.9099. Min Act: -0.0000

Data Index: 645419 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 2.5261. Min Range: -2.5261

Max Act: 1.7491. Min Act: -0.0000

Data Index: 1089882 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 2.5261. Min Range: -2.5261

Max Act: 1.6391. Min Act: -0.0000

Data Index: 829982 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 2.5261. Min Range: -2.5261

Max Act: 1.6873. Min Act: -0.0000

Data Index: 810354 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 2.5261. Min Range: -2.5261

Max Act: 1.6418. Min Act: -0.0000

Data Index: 1298307 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 2.5261. Min Range: -2.5261

Max Act: 1.5959. Min Act: -0.0000

Data Index: 388400 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 2.5261. Min Range: -2.5261

Max Act: 1.5949. Min Act: -0.0000

Data Index: 686399 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 2.5261. Min Range: -2.5261

Max Act: 1.5488. Min Act: -0.0000

Data Index: 667201 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 2.5261. Min Range: -2.5261

Max Act: 1.5673. Min Act: -0.0000

Data Index: 156156 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 2.5261. Min Range: -2.5261

Max Act: 1.6683. Min Act: -0.0000

Data Index: 543100 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 2.5261. Min Range: -2.5261

Max Act: 1.5560. Min Act: -0.0000

Data Index: 367848 (C4 (Web Text))

Max Activating Token Index: 475