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

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

Neuron 3645 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: 0.2208. Min Range: -0.2208

Max Act: 0.2208. Min Act: -0.0000

Data Index: 806208 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1957. Min Act: -0.0000

Data Index: 510779 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1955. Min Act: -0.0000

Data Index: 983977 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1825. Min Act: -0.0000

Data Index: 403039 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1696. Min Act: -0.0001

Data Index: 391959 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1652. Min Act: -0.0000

Data Index: 1261890 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1593. Min Act: -0.0001

Data Index: 208424 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1696. Min Act: -0.0001

Data Index: 1349294 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1629. Min Act: -0.0000

Data Index: 1347100 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1620. Min Act: -0.0000

Data Index: 216924 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1590. Min Act: -0.0000

Data Index: 1105677 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1578. Min Act: -0.0000

Data Index: 42632 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1576. Min Act: -0.0000

Data Index: 1045566 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1596. Min Act: -0.0001

Data Index: 101514 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1595. Min Act: -0.0000

Data Index: 9007 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1587. Min Act: -0.0001

Data Index: 279331 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1521. Min Act: -0.0000

Data Index: 376706 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1524. Min Act: -0.0000

Data Index: 1295075 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1519. Min Act: -0.0001

Data Index: 827392 (C4 (Web Text))

Max Activating Token Index: 945

Text #19

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1170644 (C4 (Web Text))

Max Activating Token Index: 217