Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1664 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2375. Min Act: -0.0005

Data Index: 349847 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2314. Min Act: -0.0005

Data Index: 541030 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2349. Min Act: -0.0005

Data Index: 296280 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2206. Min Act: -0.0005

Data Index: 1023238 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2092. Min Act: -0.0005

Data Index: 1244034 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.2006. Min Act: -0.0005

Data Index: 141438 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1937. Min Act: -0.0005

Data Index: 781089 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1928. Min Act: -0.0005

Data Index: 426767 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1869. Min Act: -0.0005

Data Index: 567240 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1835. Min Act: -0.0005

Data Index: 371334 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1763. Min Act: -0.0005

Data Index: 1295813 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1760. Min Act: -0.0005

Data Index: 1260394 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1788. Min Act: -0.0005

Data Index: 300273 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1828. Min Act: -0.0005

Data Index: 393546 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1848. Min Act: -0.0005

Data Index: 181971 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1856. Min Act: -0.0005

Data Index: 277408 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1836. Min Act: -0.0005

Data Index: 766941 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1686. Min Act: -0.0005

Data Index: 9671 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1584. Min Act: -0.0005

Data Index: 620385 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 0.2375. Min Range: -0.2375

Max Act: 0.1749. Min Act: -0.0005

Data Index: 1048506 (C4 (Web Text))

Max Activating Token Index: 59