Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3987 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.5256. Min Act: -0.0000

Data Index: 1386358 (Python Code)

Max Activating Token Index: 319

Text #1

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.6423. Min Act: -0.0000

Data Index: 1474680 (Python Code)

Max Activating Token Index: 499

Text #2

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.3125. Min Act: -0.0000

Data Index: 1603924 (Python Code)

Max Activating Token Index: 838

Text #3

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.6037. Min Act: -0.0001

Data Index: 1621163 (Python Code)

Max Activating Token Index: 539

Text #4

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.6420. Min Act: -0.0001

Data Index: 1475213 (Python Code)

Max Activating Token Index: 764

Text #5

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.2269. Min Act: -0.0000

Data Index: 1450869 (Python Code)

Max Activating Token Index: 297

Text #6

Max Range: 5.6423. Min Range: -5.6423

Max Act: 4.9591. Min Act: -0.0000

Data Index: 1444910 (Python Code)

Max Activating Token Index: 873

Text #7

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.1218. Min Act: -0.0001

Data Index: 1442728 (Python Code)

Max Activating Token Index: 727

Text #8

Max Range: 5.6423. Min Range: -5.6423

Max Act: 5.0270. Min Act: -0.0000

Data Index: 1540790 (Python Code)

Max Activating Token Index: 171

Text #9

Max Range: 5.6423. Min Range: -5.6423

Max Act: 4.7827. Min Act: -0.0000

Data Index: 1503910 (Python Code)

Max Activating Token Index: 255

Text #10

Max Range: 5.6423. Min Range: -5.6423

Max Act: 4.4259. Min Act: -0.0000

Data Index: 1541262 (Python Code)

Max Activating Token Index: 999

Text #11

Max Range: 5.6423. Min Range: -5.6423

Max Act: 4.8902. Min Act: -0.0000

Data Index: 1431666 (Python Code)

Max Activating Token Index: 501

Text #12

Max Range: 5.6423. Min Range: -5.6423

Max Act: 4.8235. Min Act: -0.0001

Data Index: 1411558 (Python Code)

Max Activating Token Index: 747

Text #13

Max Range: 5.6423. Min Range: -5.6423

Max Act: 4.4883. Min Act: -0.0000

Data Index: 1383333 (Python Code)

Max Activating Token Index: 328

Text #14

Max Range: 5.6423. Min Range: -5.6423

Max Act: 4.9898. Min Act: -0.0001

Data Index: 1433440 (Python Code)

Max Activating Token Index: 375

Text #15

Max Range: 5.6423. Min Range: -5.6423

Max Act: 4.9659. Min Act: -0.0001

Data Index: 1413197 (Python Code)

Max Activating Token Index: 784

Text #16

Max Range: 5.6423. Min Range: -5.6423

Max Act: 4.4396. Min Act: -0.0000

Data Index: 1515553 (Python Code)

Max Activating Token Index: 1007

Text #17

Max Range: 5.6423. Min Range: -5.6423

Max Act: 4.9126. Min Act: -0.0001

Data Index: 1487298 (Python Code)

Max Activating Token Index: 515

Text #18

Max Range: 5.6423. Min Range: -5.6423

Max Act: 4.5510. Min Act: -0.0001

Data Index: 1435592 (Python Code)

Max Activating Token Index: 212

Text #19

Max Range: 5.6423. Min Range: -5.6423

Max Act: 4.5520. Min Act: -0.0000

Data Index: 1579537 (Python Code)

Max Activating Token Index: 116