Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3264 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.9100. Min Act: -0.0000

Data Index: 1390342 (Python Code)

Max Activating Token Index: 678

Text #1

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.6432. Min Act: -0.0000

Data Index: 1017950 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.5336. Min Act: -0.0000

Data Index: 477588 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.4903. Min Act: -0.0000

Data Index: 646780 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.6755. Min Act: -0.0000

Data Index: 1612761 (Python Code)

Max Activating Token Index: 886

Text #5

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.6554. Min Act: -0.0000

Data Index: 870485 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.5384. Min Act: -0.0000

Data Index: 414513 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.5311. Min Act: -0.0000

Data Index: 274369 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.5004. Min Act: -0.0000

Data Index: 117418 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.4948. Min Act: -0.0000

Data Index: 815694 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.4587. Min Act: -0.0000

Data Index: 1483419 (Python Code)

Max Activating Token Index: 974

Text #11

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.4100. Min Act: -0.0000

Data Index: 85489 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.4947. Min Act: -0.0000

Data Index: 225552 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.4833. Min Act: -0.0000

Data Index: 1239371 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.4275. Min Act: -0.0000

Data Index: 1093132 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.4263. Min Act: -0.0000

Data Index: 906795 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.4242. Min Act: -0.0000

Data Index: 362365 (C4 (Web Text))

Max Activating Token Index: 456

Text #17

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.4541. Min Act: -0.0001

Data Index: 246822 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.4907. Min Act: -0.0000

Data Index: 734710 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 1.9100. Min Range: -1.9100

Max Act: 1.4029. Min Act: -0.0000

Data Index: 1113438 (C4 (Web Text))

Max Activating Token Index: 101