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

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

Neuron 5859 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5565. Min Range: -2.5565

Max Act: 2.4655. Min Act: -0.0000

Data Index: 799701 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 2.5565. Min Range: -2.5565

Max Act: 2.5565. Min Act: -0.0000

Data Index: 2412 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 2.5565. Min Range: -2.5565

Max Act: 2.3821. Min Act: -0.0000

Data Index: 324953 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 2.5565. Min Range: -2.5565

Max Act: 2.4739. Min Act: -0.0000

Data Index: 1176747 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 2.5565. Min Range: -2.5565

Max Act: 2.4428. Min Act: -0.0000

Data Index: 789207 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 2.5565. Min Range: -2.5565

Max Act: 2.4018. Min Act: -0.0000

Data Index: 240680 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 2.5565. Min Range: -2.5565

Max Act: 2.3979. Min Act: -0.0000

Data Index: 306446 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 2.5565. Min Range: -2.5565

Max Act: 2.3468. Min Act: -0.0000

Data Index: 189900 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 2.5565. Min Range: -2.5565

Max Act: 2.3388. Min Act: -0.0000

Data Index: 698746 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 2.5565. Min Range: -2.5565

Max Act: 2.2042. Min Act: -0.0000

Data Index: 615725 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 2.5565. Min Range: -2.5565

Max Act: 2.0629. Min Act: -0.0000

Data Index: 305044 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 2.5565. Min Range: -2.5565

Max Act: 2.0370. Min Act: -0.0000

Data Index: 1007506 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.9140. Min Act: -0.0000

Data Index: 938676 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 2.5565. Min Range: -2.5565

Max Act: 2.0126. Min Act: -0.0000

Data Index: 1142930 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 2.5565. Min Range: -2.5565

Max Act: 2.0149. Min Act: -0.0000

Data Index: 366904 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.9940. Min Act: -0.0000

Data Index: 284710 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.9865. Min Act: -0.0000

Data Index: 123917 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.9939. Min Act: -0.0000

Data Index: 231885 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.9975. Min Act: -0.0000

Data Index: 568872 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 2.5565. Min Range: -2.5565

Max Act: 1.9327. Min Act: -0.0000

Data Index: 47349 (C4 (Web Text))

Max Activating Token Index: 462