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

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

Neuron 1275 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.4648. Min Act: -0.0001

Data Index: 649136 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.4341. Min Act: -0.0001

Data Index: 1343858 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.4290. Min Act: -0.0001

Data Index: 172335 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.3995. Min Act: -0.0001

Data Index: 851438 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.3842. Min Act: -0.0001

Data Index: 496268 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.3662. Min Act: -0.0001

Data Index: 739249 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.3905. Min Act: -0.0001

Data Index: 1287634 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.3755. Min Act: -0.0001

Data Index: 1251062 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.3591. Min Act: -0.0001

Data Index: 320471 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.3664. Min Act: -0.0001

Data Index: 197967 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.3779. Min Act: -0.0001

Data Index: 722354 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.3658. Min Act: -0.0001

Data Index: 968621 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.3615. Min Act: -0.0001

Data Index: 1343000 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.3385. Min Act: -0.0001

Data Index: 758582 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.3498. Min Act: -0.0001

Data Index: 722524 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.3404. Min Act: -0.0001

Data Index: 268823 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.3400. Min Act: -0.0001

Data Index: 347817 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.3492. Min Act: -0.0001

Data Index: 566531 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.3142. Min Act: -0.0001

Data Index: 1079208 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.4648. Min Range: -0.4648

Max Act: 0.3228. Min Act: -0.0001

Data Index: 721117 (C4 (Web Text))

Max Activating Token Index: 373