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

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

Neuron 5000 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: 1.6494. Min Range: -1.6494

Max Act: 1.6494. Min Act: -0.0000

Data Index: 713599 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.4446. Min Act: -0.0000

Data Index: 1097329 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.5277. Min Act: -0.0000

Data Index: 1060689 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.4150. Min Act: -0.0000

Data Index: 891654 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.3209. Min Act: -0.0000

Data Index: 1068872 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.3375. Min Act: -0.0000

Data Index: 1308856 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.3364. Min Act: -0.0000

Data Index: 613376 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2342. Min Act: -0.0000

Data Index: 845466 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.3052. Min Act: -0.0000

Data Index: 860413 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2861. Min Act: -0.0000

Data Index: 1124469 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.3578. Min Act: -0.0000

Data Index: 653856 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.1842. Min Act: -0.0000

Data Index: 399908 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2362. Min Act: -0.0000

Data Index: 526408 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2285. Min Act: -0.0000

Data Index: 655528 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2153. Min Act: -0.0000

Data Index: 311793 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2553. Min Act: -0.0000

Data Index: 402431 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.1738. Min Act: -0.0000

Data Index: 10225 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.1028. Min Act: -0.0000

Data Index: 216679 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.2439. Min Act: -0.0000

Data Index: 30914 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 1.6494. Min Range: -1.6494

Max Act: 1.1666. Min Act: -0.0000

Data Index: 925934 (C4 (Web Text))

Max Activating Token Index: 292