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

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

Neuron 4389 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0563. Min Act: -0.0001

Data Index: 477846 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0599. Min Act: -0.0001

Data Index: 1429555 (Python Code)

Max Activating Token Index: 123

Text #2

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0600. Min Act: -0.0001

Data Index: 946172 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0384. Min Act: -0.0001

Data Index: 1171882 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0437. Min Act: -0.0001

Data Index: 449041 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0324. Min Act: -0.0001

Data Index: 675877 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0384. Min Act: -0.0001

Data Index: 1519639 (Python Code)

Max Activating Token Index: 425

Text #7

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0425. Min Act: -0.0001

Data Index: 842359 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0355. Min Act: -0.0001

Data Index: 337423 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0372. Min Act: -0.0001

Data Index: 1343892 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0334. Min Act: -0.0001

Data Index: 1468792 (Python Code)

Max Activating Token Index: 792

Text #11

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0326. Min Act: -0.0001

Data Index: 808281 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0368. Min Act: -0.0001

Data Index: 510230 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0362. Min Act: -0.0001

Data Index: 552734 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0404. Min Act: -0.0001

Data Index: 673988 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0363. Min Act: -0.0001

Data Index: 1230516 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0372. Min Act: -0.0001

Data Index: 479994 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0359. Min Act: -0.0001

Data Index: 1081557 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0332. Min Act: -0.0001

Data Index: 709280 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0358. Min Act: -0.0001

Data Index: 417658 (C4 (Web Text))

Max Activating Token Index: 834