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

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

Neuron 5007 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: 1.5869. Min Range: -1.5869

Max Act: 1.5869. Min Act: -0.0000

Data Index: 1327367 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.4809. Min Act: -0.0000

Data Index: 824843 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.4772. Min Act: -0.0000

Data Index: 709598 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.3307. Min Act: -0.0000

Data Index: 360122 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.2463. Min Act: -0.0000

Data Index: 681842 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.3178. Min Act: -0.0000

Data Index: 522612 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.2684. Min Act: -0.0000

Data Index: 313108 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.2293. Min Act: -0.0000

Data Index: 1125920 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.2750. Min Act: -0.0000

Data Index: 419002 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.3477. Min Act: -0.0000

Data Index: 636134 (C4 (Web Text))

Max Activating Token Index: 764

Text #10

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.2346. Min Act: -0.0000

Data Index: 250028 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.1930. Min Act: -0.0000

Data Index: 270435 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.3941. Min Act: -0.0000

Data Index: 1315819 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.2605. Min Act: -0.0000

Data Index: 1856 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.2015. Min Act: -0.0000

Data Index: 593600 (C4 (Web Text))

Max Activating Token Index: 716

Text #15

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.1913. Min Act: -0.0000

Data Index: 294999 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.1594. Min Act: -0.0000

Data Index: 428090 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.1889. Min Act: -0.0000

Data Index: 196268 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.2266. Min Act: -0.0000

Data Index: 1100320 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 1.5869. Min Range: -1.5869

Max Act: 1.2188. Min Act: -0.0000

Data Index: 1074392 (C4 (Web Text))

Max Activating Token Index: 557