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

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

Neuron 322 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.7209. Min Act: -0.0000

Data Index: 571591 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.7386. Min Act: -0.0000

Data Index: 752834 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.7043. Min Act: -0.0000

Data Index: 152225 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.6386. Min Act: -0.0000

Data Index: 686099 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.6142. Min Act: -0.0000

Data Index: 40602 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5914. Min Act: -0.0000

Data Index: 570043 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.6358. Min Act: -0.0000

Data Index: 694414 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.6042. Min Act: -0.0000

Data Index: 786125 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5794. Min Act: 0.0000

Data Index: 1139921 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.6091. Min Act: -0.0000

Data Index: 617176 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5467. Min Act: -0.0000

Data Index: 522611 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1300564 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5714. Min Act: -0.0000

Data Index: 194469 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5883. Min Act: -0.0000

Data Index: 267383 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5626. Min Act: -0.0000

Data Index: 827974 (C4 (Web Text))

Max Activating Token Index: 622

Text #15

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1035223 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5474. Min Act: -0.0000

Data Index: 1273351 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5425. Min Act: -0.0000

Data Index: 692028 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5236. Min Act: -0.0000

Data Index: 1338809 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.7386. Min Range: -0.7386

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1125749 (C4 (Web Text))

Max Activating Token Index: 145