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

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

Neuron 3683 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: 3.6255. Min Range: -3.6255

Max Act: 3.5873. Min Act: -0.0000

Data Index: 1426958 (Python Code)

Max Activating Token Index: 419

Text #1

Max Range: 3.6255. Min Range: -3.6255

Max Act: 3.6255. Min Act: -0.0000

Data Index: 1522846 (Python Code)

Max Activating Token Index: 663

Text #2

Max Range: 3.6255. Min Range: -3.6255

Max Act: 2.9969. Min Act: -0.0000

Data Index: 1489592 (Python Code)

Max Activating Token Index: 100

Text #3

Max Range: 3.6255. Min Range: -3.6255

Max Act: 2.8428. Min Act: -0.0000

Data Index: 1464417 (Python Code)

Max Activating Token Index: 579

Text #4

Max Range: 3.6255. Min Range: -3.6255

Max Act: 2.7317. Min Act: -0.0000

Data Index: 1526884 (Python Code)

Max Activating Token Index: 719

Text #5

Max Range: 3.6255. Min Range: -3.6255

Max Act: 2.7041. Min Act: -0.0000

Data Index: 1475882 (Python Code)

Max Activating Token Index: 311

Text #6

Max Range: 3.6255. Min Range: -3.6255

Max Act: 2.6265. Min Act: -0.0000

Data Index: 1635198 (Python Code)

Max Activating Token Index: 1016

Text #7

Max Range: 3.6255. Min Range: -3.6255

Max Act: 2.5953. Min Act: -0.0000

Data Index: 1390316 (Python Code)

Max Activating Token Index: 516

Text #8

Max Range: 3.6255. Min Range: -3.6255

Max Act: 2.5701. Min Act: -0.0000

Data Index: 1651552 (Python Code)

Max Activating Token Index: 607

Text #9

Max Range: 3.6255. Min Range: -3.6255

Max Act: 2.5681. Min Act: -0.0000

Data Index: 1439173 (Python Code)

Max Activating Token Index: 1001

Text #10

Max Range: 3.6255. Min Range: -3.6255

Max Act: 2.6963. Min Act: -0.0000

Data Index: 1640539 (Python Code)

Max Activating Token Index: 682

Text #11

Max Range: 3.6255. Min Range: -3.6255

Max Act: 2.5405. Min Act: -0.0000

Data Index: 1578215 (Python Code)

Max Activating Token Index: 740

Text #12

Max Range: 3.6255. Min Range: -3.6255

Max Act: 2.4174. Min Act: -0.0000

Data Index: 1488016 (Python Code)

Max Activating Token Index: 1015

Text #13

Max Range: 3.6255. Min Range: -3.6255

Max Act: 2.5256. Min Act: -0.0000

Data Index: 1535853 (Python Code)

Max Activating Token Index: 834

Text #14

Max Range: 3.6255. Min Range: -3.6255

Max Act: 2.6644. Min Act: -0.0000

Data Index: 1536181 (Python Code)

Max Activating Token Index: 312

Text #15

Max Range: 3.6255. Min Range: -3.6255

Max Act: 2.5019. Min Act: -0.0000

Data Index: 1578351 (Python Code)

Max Activating Token Index: 963

Text #16

Max Range: 3.6255. Min Range: -3.6255

Max Act: 2.3643. Min Act: -0.0000

Data Index: 1637939 (Python Code)

Max Activating Token Index: 157

Text #17

Max Range: 3.6255. Min Range: -3.6255

Max Act: 2.4766. Min Act: -0.0000

Data Index: 1544470 (Python Code)

Max Activating Token Index: 382

Text #18

Max Range: 3.6255. Min Range: -3.6255

Max Act: 2.4102. Min Act: -0.0000

Data Index: 1468926 (Python Code)

Max Activating Token Index: 140

Text #19

Max Range: 3.6255. Min Range: -3.6255

Max Act: 2.3931. Min Act: -0.0000

Data Index: 1649814 (Python Code)

Max Activating Token Index: 683