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

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

Neuron 946 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1892. Min Range: -3.1892

Max Act: 3.1892. Min Act: 0.0000

Data Index: 1568217 (Python Code)

Max Activating Token Index: 74

Text #1

Max Range: 3.1892. Min Range: -3.1892

Max Act: 2.5250. Min Act: -0.0000

Data Index: 1493898 (Python Code)

Max Activating Token Index: 581

Text #2

Max Range: 3.1892. Min Range: -3.1892

Max Act: 2.4425. Min Act: 0.0000

Data Index: 1420672 (Python Code)

Max Activating Token Index: 119

Text #3

Max Range: 3.1892. Min Range: -3.1892

Max Act: 2.1930. Min Act: 0.0000

Data Index: 1414562 (Python Code)

Max Activating Token Index: 417

Text #4

Max Range: 3.1892. Min Range: -3.1892

Max Act: 2.2401. Min Act: -0.0000

Data Index: 1488963 (Python Code)

Max Activating Token Index: 218

Text #5

Max Range: 3.1892. Min Range: -3.1892

Max Act: 2.2158. Min Act: 0.0001

Data Index: 1564262 (Python Code)

Max Activating Token Index: 1008

Text #6

Max Range: 3.1892. Min Range: -3.1892

Max Act: 2.2618. Min Act: -0.0000

Data Index: 1373372 (Python Code)

Max Activating Token Index: 20

Text #7

Max Range: 3.1892. Min Range: -3.1892

Max Act: 2.1558. Min Act: -0.0000

Data Index: 1641936 (Python Code)

Max Activating Token Index: 217

Text #8

Max Range: 3.1892. Min Range: -3.1892

Max Act: 2.1479. Min Act: -0.0000

Data Index: 1538565 (Python Code)

Max Activating Token Index: 29

Text #9

Max Range: 3.1892. Min Range: -3.1892

Max Act: 2.0239. Min Act: -0.0000

Data Index: 1418828 (Python Code)

Max Activating Token Index: 495

Text #10

Max Range: 3.1892. Min Range: -3.1892

Max Act: 2.0843. Min Act: -0.0000

Data Index: 1590222 (Python Code)

Max Activating Token Index: 582

Text #11

Max Range: 3.1892. Min Range: -3.1892

Max Act: 2.0720. Min Act: 0.0001

Data Index: 1495032 (Python Code)

Max Activating Token Index: 336

Text #12

Max Range: 3.1892. Min Range: -3.1892

Max Act: 1.9233. Min Act: 0.0001

Data Index: 1457915 (Python Code)

Max Activating Token Index: 938

Text #13

Max Range: 3.1892. Min Range: -3.1892

Max Act: 2.0974. Min Act: -0.0000

Data Index: 1611479 (Python Code)

Max Activating Token Index: 1019

Text #14

Max Range: 3.1892. Min Range: -3.1892

Max Act: 1.9586. Min Act: -0.0000

Data Index: 1440467 (Python Code)

Max Activating Token Index: 554

Text #15

Max Range: 3.1892. Min Range: -3.1892

Max Act: 1.9304. Min Act: 0.0001

Data Index: 1620434 (Python Code)

Max Activating Token Index: 799

Text #16

Max Range: 3.1892. Min Range: -3.1892

Max Act: 1.7523. Min Act: 0.0001

Data Index: 1408676 (Python Code)

Max Activating Token Index: 88

Text #17

Max Range: 3.1892. Min Range: -3.1892

Max Act: 1.8250. Min Act: 0.0000

Data Index: 1639942 (Python Code)

Max Activating Token Index: 537

Text #18

Max Range: 3.1892. Min Range: -3.1892

Max Act: 1.8269. Min Act: -0.0000

Data Index: 1495416 (Python Code)

Max Activating Token Index: 527

Text #19

Max Range: 3.1892. Min Range: -3.1892

Max Act: 1.9554. Min Act: -0.0000

Data Index: 1494594 (Python Code)

Max Activating Token Index: 884