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

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

Neuron 3558 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.4797. Min Act: -0.0000

Data Index: 732195 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.2004. Min Act: -0.0000

Data Index: 1156032 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.2661. Min Act: -0.0000

Data Index: 420771 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.1145. Min Act: -0.0000

Data Index: 1165079 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.1338. Min Act: -0.0000

Data Index: 421194 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.1286. Min Act: -0.0000

Data Index: 262626 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.1413. Min Act: -0.0000

Data Index: 530362 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0935. Min Act: -0.0000

Data Index: 205738 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0730. Min Act: -0.0000

Data Index: 280084 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0671. Min Act: -0.0000

Data Index: 1333127 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0012. Min Act: -0.0000

Data Index: 21189 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0161. Min Act: -0.0000

Data Index: 1339192 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0031. Min Act: -0.0000

Data Index: 845132 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 1.4797. Min Range: -1.4797

Max Act: 0.9903. Min Act: -0.0000

Data Index: 17317 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0573. Min Act: -0.0000

Data Index: 596364 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 1.4797. Min Range: -1.4797

Max Act: 0.9033. Min Act: -0.0000

Data Index: 793976 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 1.4797. Min Range: -1.4797

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1210123 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 1.4797. Min Range: -1.4797

Max Act: 0.8750. Min Act: -0.0000

Data Index: 1265699 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 1.4797. Min Range: -1.4797

Max Act: 0.8246. Min Act: -0.0000

Data Index: 1026711 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 1.4797. Min Range: -1.4797

Max Act: 0.8200. Min Act: -0.0000

Data Index: 237478 (C4 (Web Text))

Max Activating Token Index: 839