Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1669 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.4274. Min Act: -0.0000

Data Index: 758918 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3895. Min Act: -0.0001

Data Index: 1270480 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3657. Min Act: -0.0001

Data Index: 325790 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3363. Min Act: -0.0001

Data Index: 849798 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.3045. Min Act: -0.0001

Data Index: 1245934 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2637. Min Act: -0.0001

Data Index: 692200 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2864. Min Act: -0.0000

Data Index: 44561 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2815. Min Act: -0.0001

Data Index: 615859 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2926. Min Act: -0.0001

Data Index: 253329 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2596. Min Act: -0.0001

Data Index: 890640 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2578. Min Act: -0.0001

Data Index: 368631 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2572. Min Act: -0.0000

Data Index: 85447 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2532. Min Act: -0.0000

Data Index: 768297 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2608. Min Act: -0.0001

Data Index: 1290636 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2424. Min Act: -0.0000

Data Index: 396506 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2498. Min Act: -0.0001

Data Index: 606169 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2498. Min Act: -0.0001

Data Index: 586695 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2380. Min Act: -0.0001

Data Index: 1159669 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2469. Min Act: -0.0001

Data Index: 354885 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 0.4274. Min Range: -0.4274

Max Act: 0.2371. Min Act: -0.0000

Data Index: 290610 (C4 (Web Text))

Max Activating Token Index: 47