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

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

Neuron 4861 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.3362. Min Act: -0.0001

Data Index: 582879 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.3011. Min Act: -0.0000

Data Index: 249626 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.2546. Min Act: -0.0000

Data Index: 821065 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.2604. Min Act: -0.0001

Data Index: 1115114 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.2222. Min Act: -0.0000

Data Index: 1235631 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.2577. Min Act: -0.0001

Data Index: 1301622 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.2411. Min Act: -0.0001

Data Index: 535832 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.2293. Min Act: -0.0001

Data Index: 517379 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.2398. Min Act: -0.0000

Data Index: 773399 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.2116. Min Act: -0.0000

Data Index: 126051 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.2126. Min Act: -0.0001

Data Index: 399850 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.2126. Min Act: -0.0000

Data Index: 553955 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.2199. Min Act: -0.0000

Data Index: 492026 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.2329. Min Act: -0.0000

Data Index: 898434 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.2080. Min Act: -0.0000

Data Index: 22592 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1098912 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.2007. Min Act: -0.0000

Data Index: 137014 (C4 (Web Text))

Max Activating Token Index: 784

Text #17

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.1878. Min Act: -0.0000

Data Index: 784915 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.1944. Min Act: -0.0000

Data Index: 304332 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 0.3362. Min Range: -0.3362

Max Act: 0.2136. Min Act: -0.0000

Data Index: 632858 (C4 (Web Text))

Max Activating Token Index: 424