Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2411 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4979. Min Act: -0.0001

Data Index: 1415321 (Python Code)

Max Activating Token Index: 386

Text #1

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1573885 (Python Code)

Max Activating Token Index: 323

Text #2

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1404662 (Python Code)

Max Activating Token Index: 214

Text #3

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4300. Min Act: -0.0001

Data Index: 1403503 (Python Code)

Max Activating Token Index: 1014

Text #4

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1639229 (Python Code)

Max Activating Token Index: 316

Text #5

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4129. Min Act: -0.0000

Data Index: 1643059 (Python Code)

Max Activating Token Index: 798

Text #6

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4017. Min Act: -0.0001

Data Index: 1656092 (Python Code)

Max Activating Token Index: 708

Text #7

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3937. Min Act: -0.0000

Data Index: 1383180 (Python Code)

Max Activating Token Index: 808

Text #8

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.4119. Min Act: -0.0000

Data Index: 1456980 (Python Code)

Max Activating Token Index: 26

Text #9

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3966. Min Act: -0.0001

Data Index: 1375800 (Python Code)

Max Activating Token Index: 31

Text #10

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1612468 (Python Code)

Max Activating Token Index: 21

Text #11

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3869. Min Act: -0.0001

Data Index: 1418409 (Python Code)

Max Activating Token Index: 537

Text #12

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3762. Min Act: -0.0000

Data Index: 1485100 (Python Code)

Max Activating Token Index: 958

Text #13

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3747. Min Act: -0.0001

Data Index: 1544905 (Python Code)

Max Activating Token Index: 986

Text #14

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3590. Min Act: -0.0000

Data Index: 1176945 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3685. Min Act: -0.0000

Data Index: 1367746 (Python Code)

Max Activating Token Index: 68

Text #16

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3642. Min Act: -0.0000

Data Index: 1643742 (Python Code)

Max Activating Token Index: 32

Text #17

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1373684 (Python Code)

Max Activating Token Index: 164

Text #18

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3451. Min Act: -0.0000

Data Index: 191961 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 0.4979. Min Range: -0.4979

Max Act: 0.3472. Min Act: -0.0000

Data Index: 1568356 (Python Code)

Max Activating Token Index: 717