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

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

Neuron 3359 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1576146 (Python Code)

Max Activating Token Index: 424

Text #1

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.8301. Min Act: -0.0000

Data Index: 1504407 (Python Code)

Max Activating Token Index: 780

Text #2

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.8097. Min Act: -0.0000

Data Index: 1512776 (Python Code)

Max Activating Token Index: 193

Text #3

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1601580 (Python Code)

Max Activating Token Index: 187

Text #4

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1378893 (Python Code)

Max Activating Token Index: 660

Text #5

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1583621 (Python Code)

Max Activating Token Index: 362

Text #6

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.7558. Min Act: 0.0000

Data Index: 1641292 (Python Code)

Max Activating Token Index: 529

Text #7

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.7315. Min Act: -0.0000

Data Index: 1609716 (Python Code)

Max Activating Token Index: 492

Text #8

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6828. Min Act: -0.0000

Data Index: 1417095 (Python Code)

Max Activating Token Index: 363

Text #9

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6784. Min Act: -0.0000

Data Index: 1395504 (Python Code)

Max Activating Token Index: 622

Text #10

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.7121. Min Act: 0.0000

Data Index: 1600587 (Python Code)

Max Activating Token Index: 962

Text #11

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6757. Min Act: -0.0000

Data Index: 1593631 (Python Code)

Max Activating Token Index: 286

Text #12

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1371386 (Python Code)

Max Activating Token Index: 967

Text #13

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6388. Min Act: 0.0000

Data Index: 1421035 (Python Code)

Max Activating Token Index: 301

Text #14

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6873. Min Act: 0.0001

Data Index: 1613798 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1362329 (Python Code)

Max Activating Token Index: 738

Text #16

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6353. Min Act: -0.0000

Data Index: 1543231 (Python Code)

Max Activating Token Index: 479

Text #17

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1469858 (Python Code)

Max Activating Token Index: 611

Text #18

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6296. Min Act: 0.0000

Data Index: 1554094 (Python Code)

Max Activating Token Index: 254

Text #19

Max Range: 0.9303. Min Range: -0.9303

Max Act: 0.6249. Min Act: -0.0000

Data Index: 346551 (C4 (Web Text))

Max Activating Token Index: 55