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

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

Neuron 4329 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: 0.1552. Min Range: -0.1552

Max Act: 0.1552. Min Act: -0.0002

Data Index: 845542 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1513. Min Act: -0.0002

Data Index: 1205330 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1471. Min Act: -0.0003

Data Index: 699030 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1436. Min Act: -0.0003

Data Index: 525738 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1424. Min Act: -0.0002

Data Index: 618996 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1397. Min Act: -0.0003

Data Index: 579243 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1355. Min Act: -0.0003

Data Index: 812254 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1357. Min Act: -0.0002

Data Index: 212805 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1346. Min Act: -0.0002

Data Index: 1090437 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1319. Min Act: -0.0002

Data Index: 820765 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1291. Min Act: -0.0002

Data Index: 1083155 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1303. Min Act: -0.0002

Data Index: 342479 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1292. Min Act: -0.0002

Data Index: 910606 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1299. Min Act: -0.0002

Data Index: 417328 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1296. Min Act: -0.0002

Data Index: 893633 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1272. Min Act: -0.0002

Data Index: 105892 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1289. Min Act: -0.0003

Data Index: 993650 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1269. Min Act: -0.0002

Data Index: 1203472 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1265. Min Act: -0.0003

Data Index: 460964 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.1552. Min Range: -0.1552

Max Act: 0.1263. Min Act: -0.0002

Data Index: 1135375 (C4 (Web Text))

Max Activating Token Index: 624