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

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

Neuron 2855 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.4498. Min Range: -4.4498

Max Act: 4.2357. Min Act: -0.0000

Data Index: 1550663 (Python Code)

Max Activating Token Index: 227

Text #1

Max Range: 4.4498. Min Range: -4.4498

Max Act: 4.1319. Min Act: -0.0000

Data Index: 1564489 (Python Code)

Max Activating Token Index: 484

Text #2

Max Range: 4.4498. Min Range: -4.4498

Max Act: 4.4346. Min Act: -0.0000

Data Index: 1410531 (Python Code)

Max Activating Token Index: 327

Text #3

Max Range: 4.4498. Min Range: -4.4498

Max Act: 4.4498. Min Act: -0.0000

Data Index: 1648483 (Python Code)

Max Activating Token Index: 219

Text #4

Max Range: 4.4498. Min Range: -4.4498

Max Act: 4.4243. Min Act: -0.0000

Data Index: 1582896 (Python Code)

Max Activating Token Index: 200

Text #5

Max Range: 4.4498. Min Range: -4.4498

Max Act: 4.1292. Min Act: -0.0000

Data Index: 1376285 (Python Code)

Max Activating Token Index: 129

Text #6

Max Range: 4.4498. Min Range: -4.4498

Max Act: 4.1295. Min Act: -0.0000

Data Index: 1391599 (Python Code)

Max Activating Token Index: 232

Text #7

Max Range: 4.4498. Min Range: -4.4498

Max Act: 3.9647. Min Act: -0.0000

Data Index: 922667 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 4.4498. Min Range: -4.4498

Max Act: 3.9287. Min Act: -0.0000

Data Index: 440485 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 4.4498. Min Range: -4.4498

Max Act: 3.9041. Min Act: -0.0000

Data Index: 1032748 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 4.4498. Min Range: -4.4498

Max Act: 3.7572. Min Act: -0.0000

Data Index: 1638854 (Python Code)

Max Activating Token Index: 58

Text #11

Max Range: 4.4498. Min Range: -4.4498

Max Act: 3.7090. Min Act: -0.0000

Data Index: 1474790 (Python Code)

Max Activating Token Index: 28

Text #12

Max Range: 4.4498. Min Range: -4.4498

Max Act: 3.7144. Min Act: -0.0000

Data Index: 1375533 (Python Code)

Max Activating Token Index: 890

Text #13

Max Range: 4.4498. Min Range: -4.4498

Max Act: 3.9225. Min Act: -0.0000

Data Index: 1522293 (Python Code)

Max Activating Token Index: 947

Text #14

Max Range: 4.4498. Min Range: -4.4498

Max Act: 3.7888. Min Act: -0.0000

Data Index: 1429905 (Python Code)

Max Activating Token Index: 713

Text #15

Max Range: 4.4498. Min Range: -4.4498

Max Act: 3.6494. Min Act: -0.0000

Data Index: 1437227 (Python Code)

Max Activating Token Index: 842

Text #16

Max Range: 4.4498. Min Range: -4.4498

Max Act: 3.5066. Min Act: -0.0000

Data Index: 1622674 (Python Code)

Max Activating Token Index: 904

Text #17

Max Range: 4.4498. Min Range: -4.4498

Max Act: 3.6630. Min Act: -0.0000

Data Index: 1565355 (Python Code)

Max Activating Token Index: 454

Text #18

Max Range: 4.4498. Min Range: -4.4498

Max Act: 3.5968. Min Act: -0.0000

Data Index: 1484810 (Python Code)

Max Activating Token Index: 124

Text #19

Max Range: 4.4498. Min Range: -4.4498

Max Act: 3.4527. Min Act: -0.0000

Data Index: 1504262 (Python Code)

Max Activating Token Index: 397