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

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

Neuron 3214 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.3293. Min Act: -0.0000

Data Index: 1456611 (Python Code)

Max Activating Token Index: 413

Text #1

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.4199. Min Act: -0.0000

Data Index: 1537079 (Python Code)

Max Activating Token Index: 687

Text #2

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.1048. Min Act: -0.0000

Data Index: 1075029 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.1574. Min Act: -0.0000

Data Index: 1447509 (Python Code)

Max Activating Token Index: 864

Text #4

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.0835. Min Act: -0.0000

Data Index: 1544172 (Python Code)

Max Activating Token Index: 189

Text #5

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.0439. Min Act: -0.0000

Data Index: 1314322 (C4 (Web Text))

Max Activating Token Index: 501

Text #6

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.0234. Min Act: -0.0000

Data Index: 1513925 (Python Code)

Max Activating Token Index: 33

Text #7

Max Range: 1.4199. Min Range: -1.4199

Max Act: 0.9851. Min Act: -0.0000

Data Index: 476523 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 1.4199. Min Range: -1.4199

Max Act: 0.9870. Min Act: -0.0000

Data Index: 736254 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 1.4199. Min Range: -1.4199

Max Act: 1.0141. Min Act: -0.0000

Data Index: 1064315 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 1.4199. Min Range: -1.4199

Max Act: 0.9920. Min Act: -0.0000

Data Index: 1651595 (Python Code)

Max Activating Token Index: 101

Text #11

Max Range: 1.4199. Min Range: -1.4199

Max Act: 0.9922. Min Act: -0.0000

Data Index: 1079732 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 1.4199. Min Range: -1.4199

Max Act: 0.9191. Min Act: -0.0000

Data Index: 1479443 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 1.4199. Min Range: -1.4199

Max Act: 0.8643. Min Act: -0.0000

Data Index: 1383405 (Python Code)

Max Activating Token Index: 122

Text #14

Max Range: 1.4199. Min Range: -1.4199

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1570374 (Python Code)

Max Activating Token Index: 240

Text #15

Max Range: 1.4199. Min Range: -1.4199

Max Act: 0.9409. Min Act: -0.0000

Data Index: 1558373 (Python Code)

Max Activating Token Index: 312

Text #16

Max Range: 1.4199. Min Range: -1.4199

Max Act: 0.9544. Min Act: -0.0000

Data Index: 1599366 (Python Code)

Max Activating Token Index: 487

Text #17

Max Range: 1.4199. Min Range: -1.4199

Max Act: 0.9454. Min Act: -0.0000

Data Index: 1423544 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 1.4199. Min Range: -1.4199

Max Act: 0.9374. Min Act: -0.0000

Data Index: 625086 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 1.4199. Min Range: -1.4199

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1301596 (C4 (Web Text))

Max Activating Token Index: 642