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

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

Neuron 476 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0303. Min Act: -0.0001

Data Index: 1618605 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1252044 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0241. Min Act: -0.0001

Data Index: 1408776 (Python Code)

Max Activating Token Index: 586

Text #3

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0239. Min Act: -0.0001

Data Index: 1619003 (Python Code)

Max Activating Token Index: 806

Text #4

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0239. Min Act: -0.0001

Data Index: 1619223 (Python Code)

Max Activating Token Index: 492

Text #5

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1457115 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0230. Min Act: -0.0001

Data Index: 1646771 (Python Code)

Max Activating Token Index: 31

Text #7

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1613536 (Python Code)

Max Activating Token Index: 659

Text #8

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0229. Min Act: -0.0001

Data Index: 962634 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0224. Min Act: -0.0001

Data Index: 1562675 (Python Code)

Max Activating Token Index: 710

Text #10

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1510898 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0222. Min Act: -0.0001

Data Index: 1547671 (Python Code)

Max Activating Token Index: 60

Text #12

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0221. Min Act: -0.0001

Data Index: 1534844 (Python Code)

Max Activating Token Index: 576

Text #13

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0221. Min Act: -0.0001

Data Index: 1379061 (Python Code)

Max Activating Token Index: 87

Text #14

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0216. Min Act: -0.0001

Data Index: 1584550 (Python Code)

Max Activating Token Index: 694

Text #15

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0218. Min Act: -0.0001

Data Index: 1572495 (Python Code)

Max Activating Token Index: 572

Text #16

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0221. Min Act: -0.0001

Data Index: 1363092 (Python Code)

Max Activating Token Index: 158

Text #17

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0218. Min Act: -0.0001

Data Index: 72307 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0217. Min Act: -0.0001

Data Index: 1473671 (Python Code)

Max Activating Token Index: 459

Text #19

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0218. Min Act: -0.0001

Data Index: 1647209 (Python Code)

Max Activating Token Index: 52