Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3709 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4722. Min Act: -0.0000

Data Index: 693803 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4619. Min Act: -0.0001

Data Index: 990901 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1041913 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1189875 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4234. Min Act: -0.0001

Data Index: 504961 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.4219. Min Act: -0.0000

Data Index: 1317430 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3563. Min Act: -0.0000

Data Index: 656144 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1267758 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3125. Min Act: -0.0000

Data Index: 1199266 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.3306. Min Act: -0.0001

Data Index: 117907 (C4 (Web Text))

Max Activating Token Index: 967

Text #10

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.2998. Min Act: -0.0000

Data Index: 1338550 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.2922. Min Act: -0.0000

Data Index: 402787 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.2856. Min Act: -0.0000

Data Index: 616479 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.2786. Min Act: -0.0001

Data Index: 39439 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.2706. Min Act: -0.0001

Data Index: 1074186 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.2711. Min Act: -0.0001

Data Index: 498027 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1035829 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.2859. Min Act: -0.0001

Data Index: 862094 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1028701 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 0.4722. Min Range: -0.4722

Max Act: 0.2616. Min Act: -0.0000

Data Index: 657220 (C4 (Web Text))

Max Activating Token Index: 544