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

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

Neuron 2000 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1316. Min Act: -0.0000

Data Index: 408756 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1096. Min Act: -0.0000

Data Index: 288325 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1053. Min Act: -0.0000

Data Index: 1084619 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0980. Min Act: -0.0000

Data Index: 1356370 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0981. Min Act: -0.0000

Data Index: 644146 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0955. Min Act: -0.0000

Data Index: 1350221 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0922. Min Act: -0.0000

Data Index: 69341 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0933. Min Act: -0.0000

Data Index: 593732 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0895. Min Act: -0.0000

Data Index: 588439 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0865. Min Act: -0.0000

Data Index: 420414 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0878. Min Act: -0.0000

Data Index: 1161732 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0769. Min Act: -0.0000

Data Index: 490857 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0809. Min Act: -0.0000

Data Index: 1300435 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0848. Min Act: -0.0000

Data Index: 896900 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0842. Min Act: -0.0000

Data Index: 82994 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0747. Min Act: -0.0000

Data Index: 869288 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0848. Min Act: -0.0000

Data Index: 427267 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0825. Min Act: -0.0000

Data Index: 322313 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0812. Min Act: -0.0000

Data Index: 274351 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.0765. Min Act: -0.0000

Data Index: 582103 (C4 (Web Text))

Max Activating Token Index: 278