Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 587 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.2031. Min Act: -0.0002

Data Index: 532795 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1999. Min Act: -0.0003

Data Index: 224390 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1972. Min Act: -0.0002

Data Index: 964258 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1974. Min Act: -0.0003

Data Index: 380682 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1942. Min Act: -0.0002

Data Index: 1098322 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1883. Min Act: -0.0002

Data Index: 548888 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1914. Min Act: -0.0002

Data Index: 946605 (C4 (Web Text))

Max Activating Token Index: 343

Text #7

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1869. Min Act: -0.0002

Data Index: 648120 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1841. Min Act: -0.0002

Data Index: 186558 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1845. Min Act: -0.0002

Data Index: 1211937 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1838. Min Act: -0.0002

Data Index: 725383 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1816. Min Act: -0.0002

Data Index: 595387 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1819. Min Act: -0.0003

Data Index: 404250 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1846. Min Act: -0.0003

Data Index: 1066927 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1819. Min Act: -0.0002

Data Index: 450830 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1842. Min Act: -0.0002

Data Index: 761195 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1804. Min Act: -0.0002

Data Index: 202032 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1795. Min Act: -0.0002

Data Index: 241271 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1772. Min Act: -0.0002

Data Index: 600311 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1776. Min Act: -0.0002

Data Index: 611215 (C4 (Web Text))

Max Activating Token Index: 532