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

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

Neuron 5027 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: 4.2693. Min Range: -4.2693

Max Act: 4.2693. Min Act: -0.0000

Data Index: 1523215 (Python Code)

Max Activating Token Index: 676

Text #1

Max Range: 4.2693. Min Range: -4.2693

Max Act: 3.5625. Min Act: -0.0000

Data Index: 1638491 (Python Code)

Max Activating Token Index: 394

Text #2

Max Range: 4.2693. Min Range: -4.2693

Max Act: 3.5773. Min Act: -0.0000

Data Index: 1620300 (Python Code)

Max Activating Token Index: 654

Text #3

Max Range: 4.2693. Min Range: -4.2693

Max Act: 3.4023. Min Act: -0.0000

Data Index: 1528795 (Python Code)

Max Activating Token Index: 381

Text #4

Max Range: 4.2693. Min Range: -4.2693

Max Act: 3.2764. Min Act: -0.0000

Data Index: 1472016 (Python Code)

Max Activating Token Index: 822

Text #5

Max Range: 4.2693. Min Range: -4.2693

Max Act: 3.2865. Min Act: -0.0000

Data Index: 1592963 (Python Code)

Max Activating Token Index: 430

Text #6

Max Range: 4.2693. Min Range: -4.2693

Max Act: 3.2588. Min Act: -0.0000

Data Index: 1359993 (Python Code)

Max Activating Token Index: 546

Text #7

Max Range: 4.2693. Min Range: -4.2693

Max Act: 3.2468. Min Act: -0.0000

Data Index: 1484852 (Python Code)

Max Activating Token Index: 65

Text #8

Max Range: 4.2693. Min Range: -4.2693

Max Act: 3.2176. Min Act: -0.0000

Data Index: 1407105 (Python Code)

Max Activating Token Index: 136

Text #9

Max Range: 4.2693. Min Range: -4.2693

Max Act: 3.1935. Min Act: -0.0000

Data Index: 1243326 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 4.2693. Min Range: -4.2693

Max Act: 3.1427. Min Act: -0.0000

Data Index: 1641227 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 4.2693. Min Range: -4.2693

Max Act: 3.1332. Min Act: -0.0000

Data Index: 1441501 (Python Code)

Max Activating Token Index: 417

Text #12

Max Range: 4.2693. Min Range: -4.2693

Max Act: 2.9628. Min Act: -0.0000

Data Index: 1381761 (Python Code)

Max Activating Token Index: 927

Text #13

Max Range: 4.2693. Min Range: -4.2693

Max Act: 3.0949. Min Act: -0.0000

Data Index: 1467899 (Python Code)

Max Activating Token Index: 39

Text #14

Max Range: 4.2693. Min Range: -4.2693

Max Act: 2.9416. Min Act: -0.0000

Data Index: 1605257 (Python Code)

Max Activating Token Index: 745

Text #15

Max Range: 4.2693. Min Range: -4.2693

Max Act: 3.0886. Min Act: -0.0000

Data Index: 1444814 (Python Code)

Max Activating Token Index: 198

Text #16

Max Range: 4.2693. Min Range: -4.2693

Max Act: 2.9057. Min Act: -0.0000

Data Index: 1604320 (Python Code)

Max Activating Token Index: 222

Text #17

Max Range: 4.2693. Min Range: -4.2693

Max Act: 2.9068. Min Act: -0.0000

Data Index: 1388097 (Python Code)

Max Activating Token Index: 318

Text #18

Max Range: 4.2693. Min Range: -4.2693

Max Act: 3.0161. Min Act: -0.0000

Data Index: 1453883 (Python Code)

Max Activating Token Index: 733

Text #19

Max Range: 4.2693. Min Range: -4.2693

Max Act: 3.0274. Min Act: -0.0000

Data Index: 1533620 (Python Code)

Max Activating Token Index: 595