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

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

Neuron 1233 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0503. Min Range: -2.0503

Max Act: 2.0503. Min Act: -0.0000

Data Index: 1165029 (C4 (Web Text))

Max Activating Token Index: 361

Text #1

Max Range: 2.0503. Min Range: -2.0503

Max Act: 1.7890. Min Act: -0.0000

Data Index: 1276195 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 2.0503. Min Range: -2.0503

Max Act: 1.8608. Min Act: -0.0000

Data Index: 543710 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 2.0503. Min Range: -2.0503

Max Act: 1.7977. Min Act: -0.0000

Data Index: 708440 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 2.0503. Min Range: -2.0503

Max Act: 1.6984. Min Act: -0.0000

Data Index: 182112 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 2.0503. Min Range: -2.0503

Max Act: 1.5162. Min Act: -0.0000

Data Index: 1516404 (Python Code)

Max Activating Token Index: 221

Text #6

Max Range: 2.0503. Min Range: -2.0503

Max Act: 1.4378. Min Act: -0.0000

Data Index: 1214660 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 2.0503. Min Range: -2.0503

Max Act: 1.5936. Min Act: -0.0000

Data Index: 826753 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 2.0503. Min Range: -2.0503

Max Act: 1.4866. Min Act: -0.0000

Data Index: 1198106 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 2.0503. Min Range: -2.0503

Max Act: 1.4675. Min Act: -0.0000

Data Index: 762870 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 2.0503. Min Range: -2.0503

Max Act: 1.5103. Min Act: -0.0000

Data Index: 1641545 (Python Code)

Max Activating Token Index: 1007

Text #11

Max Range: 2.0503. Min Range: -2.0503

Max Act: 1.3693. Min Act: -0.0000

Data Index: 1457558 (Python Code)

Max Activating Token Index: 318

Text #12

Max Range: 2.0503. Min Range: -2.0503

Max Act: 1.3563. Min Act: -0.0000

Data Index: 186378 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 2.0503. Min Range: -2.0503

Max Act: 1.3976. Min Act: -0.0000

Data Index: 1586577 (Python Code)

Max Activating Token Index: 484

Text #14

Max Range: 2.0503. Min Range: -2.0503

Max Act: 1.3421. Min Act: -0.0000

Data Index: 1462594 (Python Code)

Max Activating Token Index: 559

Text #15

Max Range: 2.0503. Min Range: -2.0503

Max Act: 1.3905. Min Act: -0.0000

Data Index: 1581411 (Python Code)

Max Activating Token Index: 915

Text #16

Max Range: 2.0503. Min Range: -2.0503

Max Act: 1.3296. Min Act: -0.0000

Data Index: 734905 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 2.0503. Min Range: -2.0503

Max Act: 1.3307. Min Act: -0.0000

Data Index: 574227 (C4 (Web Text))

Max Activating Token Index: 446

Text #18

Max Range: 2.0503. Min Range: -2.0503

Max Act: 1.2754. Min Act: -0.0000

Data Index: 1627468 (Python Code)

Max Activating Token Index: 133

Text #19

Max Range: 2.0503. Min Range: -2.0503

Max Act: 1.2760. Min Act: -0.0000

Data Index: 335070 (C4 (Web Text))

Max Activating Token Index: 861