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

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

Neuron 5449 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8645. Min Act: -0.0000

Data Index: 325779 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1493369 (Python Code)

Max Activating Token Index: 710

Text #2

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8393. Min Act: -0.0000

Data Index: 1349856 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.9025. Min Act: -0.0000

Data Index: 1598628 (Python Code)

Max Activating Token Index: 538

Text #4

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8664. Min Act: -0.0000

Data Index: 888328 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.9159. Min Act: -0.0000

Data Index: 604497 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8545. Min Act: -0.0000

Data Index: 585588 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8351. Min Act: -0.0000

Data Index: 725113 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8734. Min Act: -0.0000

Data Index: 1368617 (Python Code)

Max Activating Token Index: 451

Text #9

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.9429. Min Act: -0.0000

Data Index: 79244 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6806. Min Act: -0.0000

Data Index: 141770 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8136. Min Act: -0.0000

Data Index: 1513562 (Python Code)

Max Activating Token Index: 334

Text #12

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8092. Min Act: -0.0000

Data Index: 1527729 (Python Code)

Max Activating Token Index: 534

Text #13

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8371. Min Act: -0.0000

Data Index: 1479510 (Python Code)

Max Activating Token Index: 662

Text #14

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7544. Min Act: -0.0000

Data Index: 1621817 (Python Code)

Max Activating Token Index: 603

Text #15

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7521. Min Act: -0.0000

Data Index: 685037 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8920. Min Act: -0.0000

Data Index: 439124 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1444951 (Python Code)

Max Activating Token Index: 928

Text #18

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1560913 (Python Code)

Max Activating Token Index: 716

Text #19

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7924. Min Act: -0.0000

Data Index: 1655592 (Python Code)

Max Activating Token Index: 671