Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 305 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5589. Min Range: -1.5589

Max Act: 1.5589. Min Act: -0.0001

Data Index: 367664 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 1.5589. Min Range: -1.5589

Max Act: 1.2418. Min Act: -0.0001

Data Index: 935126 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 1.5589. Min Range: -1.5589

Max Act: 1.2241. Min Act: -0.0001

Data Index: 869289 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 1.5589. Min Range: -1.5589

Max Act: 1.0699. Min Act: -0.0001

Data Index: 529994 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 1.5589. Min Range: -1.5589

Max Act: 1.3235. Min Act: -0.0000

Data Index: 672034 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 1.5589. Min Range: -1.5589

Max Act: 1.1230. Min Act: -0.0001

Data Index: 690205 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 1.5589. Min Range: -1.5589

Max Act: 1.1642. Min Act: -0.0001

Data Index: 1321902 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 1.5589. Min Range: -1.5589

Max Act: 1.2022. Min Act: -0.0001

Data Index: 347266 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 1.5589. Min Range: -1.5589

Max Act: 1.1815. Min Act: -0.0001

Data Index: 889847 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 1.5589. Min Range: -1.5589

Max Act: 1.1390. Min Act: -0.0001

Data Index: 113274 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 1.5589. Min Range: -1.5589

Max Act: 1.1796. Min Act: -0.0000

Data Index: 639808 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 1.5589. Min Range: -1.5589

Max Act: 1.1140. Min Act: -0.0000

Data Index: 1284758 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 1.5589. Min Range: -1.5589

Max Act: 1.1070. Min Act: -0.0001

Data Index: 848752 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 1.5589. Min Range: -1.5589

Max Act: 1.1683. Min Act: -0.0000

Data Index: 1054764 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 1.5589. Min Range: -1.5589

Max Act: 0.9519. Min Act: -0.0000

Data Index: 560515 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 1.5589. Min Range: -1.5589

Max Act: 1.1170. Min Act: -0.0000

Data Index: 448354 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 1.5589. Min Range: -1.5589

Max Act: 1.0908. Min Act: -0.0001

Data Index: 184197 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 1.5589. Min Range: -1.5589

Max Act: 1.0480. Min Act: -0.0001

Data Index: 1276671 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 1.5589. Min Range: -1.5589

Max Act: 1.0338. Min Act: -0.0001

Data Index: 411940 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 1.5589. Min Range: -1.5589

Max Act: 1.0742. Min Act: -0.0000

Data Index: 1307666 (C4 (Web Text))

Max Activating Token Index: 835