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

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

Neuron 4560 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.6552. Min Act: -0.0002

Data Index: 610588 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.6184. Min Act: -0.0002

Data Index: 1081534 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.6145. Min Act: -0.0002

Data Index: 824942 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5885. Min Act: -0.0002

Data Index: 1211118 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.6196. Min Act: -0.0002

Data Index: 786325 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5770. Min Act: -0.0002

Data Index: 833352 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5844. Min Act: -0.0002

Data Index: 443911 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5830. Min Act: -0.0002

Data Index: 358211 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.6118. Min Act: -0.0002

Data Index: 1184396 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5797. Min Act: -0.0002

Data Index: 761918 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5626. Min Act: -0.0002

Data Index: 1011823 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.6021. Min Act: -0.0002

Data Index: 1323971 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5511. Min Act: -0.0002

Data Index: 321423 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5334. Min Act: -0.0002

Data Index: 541422 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5453. Min Act: -0.0002

Data Index: 754168 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5849. Min Act: -0.0002

Data Index: 1043550 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5439. Min Act: -0.0002

Data Index: 469526 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5435. Min Act: -0.0002

Data Index: 1283326 (C4 (Web Text))

Max Activating Token Index: 890

Text #18

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5375. Min Act: -0.0002

Data Index: 1279568 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5369. Min Act: -0.0002

Data Index: 381822 (C4 (Web Text))

Max Activating Token Index: 577