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

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

Neuron 5245 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: 0.1699. Min Range: -0.1699

Max Act: 0.1699. Min Act: -0.0002

Data Index: 696122 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1612. Min Act: -0.0002

Data Index: 237904 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1501. Min Act: -0.0002

Data Index: 396279 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1505. Min Act: -0.0002

Data Index: 123328 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1485. Min Act: -0.0002

Data Index: 328362 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1479. Min Act: -0.0002

Data Index: 25216 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1449. Min Act: -0.0002

Data Index: 41756 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1476. Min Act: -0.0002

Data Index: 1083702 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1437. Min Act: -0.0002

Data Index: 298258 (C4 (Web Text))

Max Activating Token Index: 437

Text #9

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1446. Min Act: -0.0003

Data Index: 1079864 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1407. Min Act: -0.0002

Data Index: 561161 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1435. Min Act: -0.0003

Data Index: 328227 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1439. Min Act: -0.0002

Data Index: 1268388 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1385. Min Act: -0.0002

Data Index: 1038800 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1404. Min Act: -0.0002

Data Index: 1057152 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1384. Min Act: -0.0002

Data Index: 53780 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1363. Min Act: -0.0002

Data Index: 78062 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1332. Min Act: -0.0003

Data Index: 21078 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1337. Min Act: -0.0002

Data Index: 679786 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.1699. Min Range: -0.1699

Max Act: 0.1334. Min Act: -0.0002

Data Index: 354645 (C4 (Web Text))

Max Activating Token Index: 98