Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2259 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.1786. Min Act: -0.0001

Data Index: 694341 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.0969. Min Act: -0.0002

Data Index: 300459 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.1517. Min Act: -0.0002

Data Index: 1053466 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.1367. Min Act: -0.0001

Data Index: 341844 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.1342. Min Act: -0.0002

Data Index: 1269260 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.1021. Min Act: -0.0001

Data Index: 54642 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.1634. Min Act: -0.0002

Data Index: 1093974 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.1171. Min Act: -0.0002

Data Index: 964705 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.1443. Min Act: -0.0002

Data Index: 380521 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.0298. Min Act: -0.0002

Data Index: 1079206 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.0272. Min Act: -0.0002

Data Index: 772029 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.1186. Min Act: -0.0002

Data Index: 51582 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.0148. Min Act: -0.0002

Data Index: 598293 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.0416. Min Act: -0.0001

Data Index: 51105 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.1020. Min Act: -0.0002

Data Index: 656502 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.0693. Min Act: -0.0002

Data Index: 191929 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.0368. Min Act: -0.0002

Data Index: 465372 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.0237. Min Act: -0.0002

Data Index: 236605 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.1233. Min Act: -0.0002

Data Index: 1185522 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 1.1786. Min Range: -1.1786

Max Act: 1.0509. Min Act: -0.0002

Data Index: 452606 (C4 (Web Text))

Max Activating Token Index: 114