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

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

Neuron 1829 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: 0.7745. Min Range: -0.7745

Max Act: 0.7745. Min Act: -0.0000

Data Index: 1530705 (Python Code)

Max Activating Token Index: 162

Text #1

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.7271. Min Act: -0.0000

Data Index: 1401942 (Python Code)

Max Activating Token Index: 35

Text #2

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.7683. Min Act: -0.0001

Data Index: 1562794 (Python Code)

Max Activating Token Index: 135

Text #3

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6717. Min Act: -0.0000

Data Index: 1529575 (Python Code)

Max Activating Token Index: 324

Text #4

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1418273 (Python Code)

Max Activating Token Index: 574

Text #5

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6614. Min Act: -0.0001

Data Index: 1469036 (Python Code)

Max Activating Token Index: 532

Text #6

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6478. Min Act: -0.0000

Data Index: 1484660 (Python Code)

Max Activating Token Index: 348

Text #7

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6275. Min Act: -0.0000

Data Index: 1385160 (Python Code)

Max Activating Token Index: 966

Text #8

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5835. Min Act: -0.0001

Data Index: 1571712 (Python Code)

Max Activating Token Index: 549

Text #9

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.6120. Min Act: -0.0000

Data Index: 1573745 (Python Code)

Max Activating Token Index: 861

Text #10

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1508245 (Python Code)

Max Activating Token Index: 633

Text #11

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5764. Min Act: -0.0001

Data Index: 1619079 (Python Code)

Max Activating Token Index: 10

Text #12

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5829. Min Act: -0.0000

Data Index: 1594139 (Python Code)

Max Activating Token Index: 803

Text #13

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5271. Min Act: -0.0000

Data Index: 1568225 (Python Code)

Max Activating Token Index: 919

Text #14

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5513. Min Act: -0.0001

Data Index: 1419492 (Python Code)

Max Activating Token Index: 859

Text #15

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5503. Min Act: -0.0001

Data Index: 1445289 (Python Code)

Max Activating Token Index: 17

Text #16

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5436. Min Act: -0.0000

Data Index: 1446196 (Python Code)

Max Activating Token Index: 75

Text #17

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5270. Min Act: -0.0001

Data Index: 1404570 (Python Code)

Max Activating Token Index: 326

Text #18

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.4866. Min Act: -0.0000

Data Index: 1478448 (Python Code)

Max Activating Token Index: 626

Text #19

Max Range: 0.7745. Min Range: -0.7745

Max Act: 0.5211. Min Act: -0.0000

Data Index: 1623151 (Python Code)

Max Activating Token Index: 698