Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1281 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0456. Min Act: -0.0002

Data Index: 304470 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0442. Min Act: -0.0003

Data Index: 676793 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0394. Min Act: -0.0002

Data Index: 514105 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1326656 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0368. Min Act: -0.0003

Data Index: 349658 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0372. Min Act: -0.0002

Data Index: 701482 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0366. Min Act: -0.0003

Data Index: 21790 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1073813 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0356. Min Act: -0.0003

Data Index: 201579 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0357. Min Act: -0.0002

Data Index: 916314 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0354. Min Act: -0.0003

Data Index: 21591 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0358. Min Act: -0.0003

Data Index: 881699 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0353. Min Act: -0.0002

Data Index: 754380 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0358. Min Act: -0.0003

Data Index: 151550 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0354. Min Act: -0.0003

Data Index: 302407 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0351. Min Act: -0.0002

Data Index: 993982 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0352. Min Act: -0.0003

Data Index: 536647 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0356. Min Act: -0.0003

Data Index: 872280 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0353. Min Act: -0.0003

Data Index: 330139 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0352. Min Act: -0.0003

Data Index: 867466 (C4 (Web Text))

Max Activating Token Index: 516