Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1347 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5079. Min Range: -2.5079

Max Act: 2.5079. Min Act: -0.0000

Data Index: 1427531 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 2.5079. Min Range: -2.5079

Max Act: 2.4536. Min Act: -0.0000

Data Index: 1624822 (Python Code)

Max Activating Token Index: 633

Text #2

Max Range: 2.5079. Min Range: -2.5079

Max Act: 2.2206. Min Act: -0.0000

Data Index: 1393274 (Python Code)

Max Activating Token Index: 770

Text #3

Max Range: 2.5079. Min Range: -2.5079

Max Act: 2.3272. Min Act: -0.0000

Data Index: 1547597 (Python Code)

Max Activating Token Index: 811

Text #4

Max Range: 2.5079. Min Range: -2.5079

Max Act: 2.2381. Min Act: -0.0000

Data Index: 1400621 (Python Code)

Max Activating Token Index: 642

Text #5

Max Range: 2.5079. Min Range: -2.5079

Max Act: 2.1813. Min Act: -0.0000

Data Index: 1555282 (Python Code)

Max Activating Token Index: 166

Text #6

Max Range: 2.5079. Min Range: -2.5079

Max Act: 2.0442. Min Act: -0.0000

Data Index: 1614161 (Python Code)

Max Activating Token Index: 641

Text #7

Max Range: 2.5079. Min Range: -2.5079

Max Act: 2.0239. Min Act: -0.0000

Data Index: 1577145 (Python Code)

Max Activating Token Index: 874

Text #8

Max Range: 2.5079. Min Range: -2.5079

Max Act: 2.1292. Min Act: -0.0000

Data Index: 1395142 (Python Code)

Max Activating Token Index: 48

Text #9

Max Range: 2.5079. Min Range: -2.5079

Max Act: 2.0775. Min Act: -0.0000

Data Index: 1542191 (Python Code)

Max Activating Token Index: 668

Text #10

Max Range: 2.5079. Min Range: -2.5079

Max Act: 2.0612. Min Act: -0.0000

Data Index: 1636194 (Python Code)

Max Activating Token Index: 597

Text #11

Max Range: 2.5079. Min Range: -2.5079

Max Act: 2.0530. Min Act: -0.0000

Data Index: 1369984 (Python Code)

Max Activating Token Index: 377

Text #12

Max Range: 2.5079. Min Range: -2.5079

Max Act: 2.0281. Min Act: -0.0000

Data Index: 1554454 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 2.5079. Min Range: -2.5079

Max Act: 2.0143. Min Act: -0.0000

Data Index: 1414359 (Python Code)

Max Activating Token Index: 844

Text #14

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.9109. Min Act: -0.0000

Data Index: 1434842 (Python Code)

Max Activating Token Index: 421

Text #15

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.9133. Min Act: -0.0000

Data Index: 1435258 (Python Code)

Max Activating Token Index: 399

Text #16

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.9943. Min Act: -0.0000

Data Index: 1603503 (Python Code)

Max Activating Token Index: 884

Text #17

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.9694. Min Act: -0.0000

Data Index: 1618521 (Python Code)

Max Activating Token Index: 925

Text #18

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.9780. Min Act: -0.0000

Data Index: 1391309 (Python Code)

Max Activating Token Index: 548

Text #19

Max Range: 2.5079. Min Range: -2.5079

Max Act: 1.9757. Min Act: -0.0000

Data Index: 1566845 (Python Code)

Max Activating Token Index: 744