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

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

Neuron 3789 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1230944 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0450. Min Act: -0.0003

Data Index: 913425 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0404. Min Act: -0.0003

Data Index: 446096 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0432. Min Act: -0.0003

Data Index: 978375 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0409. Min Act: -0.0003

Data Index: 925572 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0415. Min Act: -0.0003

Data Index: 322912 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0401. Min Act: -0.0002

Data Index: 57925 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0405. Min Act: -0.0003

Data Index: 986902 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0422. Min Act: -0.0003

Data Index: 47610 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0362. Min Act: -0.0003

Data Index: 729024 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1343329 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0359. Min Act: -0.0003

Data Index: 472860 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0364. Min Act: -0.0003

Data Index: 236113 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0370. Min Act: -0.0002

Data Index: 1076934 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0359. Min Act: -0.0003

Data Index: 173447 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0346. Min Act: -0.0003

Data Index: 1158758 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0344. Min Act: -0.0003

Data Index: 163204 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0378. Min Act: -0.0003

Data Index: 857327 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0336. Min Act: -0.0003

Data Index: 472524 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0345. Min Act: -0.0003

Data Index: 741980 (C4 (Web Text))

Max Activating Token Index: 288