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

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

Neuron 3012 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: 0.0385. Min Range: -0.0385

Max Act: 0.0384. Min Act: -0.0002

Data Index: 5667 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0385. Min Act: -0.0003

Data Index: 968846 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0354. Min Act: -0.0002

Data Index: 341123 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0356. Min Act: -0.0002

Data Index: 619236 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0354. Min Act: -0.0002

Data Index: 910734 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1029179 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0347. Min Act: -0.0002

Data Index: 671606 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1360284 (Python Code)

Max Activating Token Index: 620

Text #8

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0345. Min Act: -0.0002

Data Index: 980532 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0346. Min Act: -0.0002

Data Index: 216623 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0346. Min Act: -0.0003

Data Index: 918850 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0341. Min Act: -0.0002

Data Index: 705164 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0342. Min Act: -0.0002

Data Index: 261111 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0342. Min Act: -0.0002

Data Index: 645341 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1309103 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0347. Min Act: -0.0002

Data Index: 903564 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0348. Min Act: -0.0003

Data Index: 1115516 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0345. Min Act: -0.0003

Data Index: 1184734 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0339. Min Act: -0.0002

Data Index: 23197 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.0385. Min Range: -0.0385

Max Act: 0.0340. Min Act: -0.0002

Data Index: 698760 (C4 (Web Text))

Max Activating Token Index: 586