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

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

Neuron 973 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.4037. Min Act: -0.0001

Data Index: 1448349 (Python Code)

Max Activating Token Index: 480

Text #1

Max Range: 3.4037. Min Range: -3.4037

Max Act: 3.2348. Min Act: -0.0001

Data Index: 1583020 (Python Code)

Max Activating Token Index: 459

Text #2

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.8333. Min Act: -0.0001

Data Index: 1609665 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.6145. Min Act: -0.0001

Data Index: 1552877 (Python Code)

Max Activating Token Index: 161

Text #4

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.6518. Min Act: -0.0001

Data Index: 1410195 (Python Code)

Max Activating Token Index: 477

Text #5

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.3274. Min Act: -0.0001

Data Index: 1621241 (Python Code)

Max Activating Token Index: 705

Text #6

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.1355. Min Act: -0.0001

Data Index: 1610505 (Python Code)

Max Activating Token Index: 961

Text #7

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.4521. Min Act: -0.0001

Data Index: 1641899 (Python Code)

Max Activating Token Index: 121

Text #8

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.4370. Min Act: -0.0001

Data Index: 1622713 (Python Code)

Max Activating Token Index: 67

Text #9

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.5594. Min Act: -0.0001

Data Index: 1626448 (Python Code)

Max Activating Token Index: 655

Text #10

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.1070. Min Act: -0.0001

Data Index: 1481772 (Python Code)

Max Activating Token Index: 884

Text #11

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.2731. Min Act: -0.0001

Data Index: 1573496 (Python Code)

Max Activating Token Index: 96

Text #12

Max Range: 3.4037. Min Range: -3.4037

Max Act: 1.9302. Min Act: -0.0001

Data Index: 1440629 (Python Code)

Max Activating Token Index: 451

Text #13

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.0833. Min Act: -0.0001

Data Index: 1416783 (Python Code)

Max Activating Token Index: 710

Text #14

Max Range: 3.4037. Min Range: -3.4037

Max Act: 1.8593. Min Act: -0.0001

Data Index: 1386760 (Python Code)

Max Activating Token Index: 248

Text #15

Max Range: 3.4037. Min Range: -3.4037

Max Act: 2.0003. Min Act: -0.0001

Data Index: 1534534 (Python Code)

Max Activating Token Index: 826

Text #16

Max Range: 3.4037. Min Range: -3.4037

Max Act: 1.9121. Min Act: -0.0001

Data Index: 1472091 (Python Code)

Max Activating Token Index: 185

Text #17

Max Range: 3.4037. Min Range: -3.4037

Max Act: 1.6890. Min Act: -0.0001

Data Index: 1655036 (Python Code)

Max Activating Token Index: 342

Text #18

Max Range: 3.4037. Min Range: -3.4037

Max Act: 1.8234. Min Act: -0.0001

Data Index: 1549508 (Python Code)

Max Activating Token Index: 859

Text #19

Max Range: 3.4037. Min Range: -3.4037

Max Act: 1.7182. Min Act: -0.0001

Data Index: 1365049 (Python Code)

Max Activating Token Index: 61