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

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

Neuron 3000 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1614. Min Range: -2.1614

Max Act: 2.1614. Min Act: -0.0000

Data Index: 754655 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 2.1614. Min Range: -2.1614

Max Act: 2.0441. Min Act: -0.0000

Data Index: 895885 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 2.1614. Min Range: -2.1614

Max Act: 1.8985. Min Act: -0.0000

Data Index: 1072983 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 2.1614. Min Range: -2.1614

Max Act: 1.6473. Min Act: -0.0000

Data Index: 812147 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 2.1614. Min Range: -2.1614

Max Act: 1.7317. Min Act: -0.0000

Data Index: 97359 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 2.1614. Min Range: -2.1614

Max Act: 1.7270. Min Act: -0.0000

Data Index: 1081374 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 2.1614. Min Range: -2.1614

Max Act: 1.6168. Min Act: -0.0000

Data Index: 211091 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 2.1614. Min Range: -2.1614

Max Act: 1.5812. Min Act: -0.0000

Data Index: 556082 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 2.1614. Min Range: -2.1614

Max Act: 1.6141. Min Act: -0.0000

Data Index: 673541 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 2.1614. Min Range: -2.1614

Max Act: 1.5293. Min Act: -0.0000

Data Index: 1208686 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 2.1614. Min Range: -2.1614

Max Act: 1.4806. Min Act: -0.0000

Data Index: 347704 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 2.1614. Min Range: -2.1614

Max Act: 1.4523. Min Act: -0.0000

Data Index: 613888 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 2.1614. Min Range: -2.1614

Max Act: 1.4315. Min Act: -0.0000

Data Index: 1194490 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 2.1614. Min Range: -2.1614

Max Act: 1.4990. Min Act: -0.0000

Data Index: 983921 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 2.1614. Min Range: -2.1614

Max Act: 1.4590. Min Act: -0.0000

Data Index: 1232915 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 2.1614. Min Range: -2.1614

Max Act: 1.5250. Min Act: -0.0000

Data Index: 418100 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 2.1614. Min Range: -2.1614

Max Act: 1.3200. Min Act: -0.0000

Data Index: 941925 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 2.1614. Min Range: -2.1614

Max Act: 1.4993. Min Act: -0.0000

Data Index: 521339 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 2.1614. Min Range: -2.1614

Max Act: 1.4748. Min Act: -0.0000

Data Index: 300268 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 2.1614. Min Range: -2.1614

Max Act: 1.3071. Min Act: -0.0000

Data Index: 1243313 (C4 (Web Text))

Max Activating Token Index: 68