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

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

Neuron 6057 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 6.8545. Min Range: -6.8545

Max Act: 6.8545. Min Act: -0.0002

Data Index: 1604982 (Python Code)

Max Activating Token Index: 27

Text #1

Max Range: 6.8545. Min Range: -6.8545

Max Act: 6.6847. Min Act: -0.0002

Data Index: 1530254 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 6.8545. Min Range: -6.8545

Max Act: 6.5550. Min Act: -0.0002

Data Index: 1538893 (Python Code)

Max Activating Token Index: 16

Text #3

Max Range: 6.8545. Min Range: -6.8545

Max Act: 6.5648. Min Act: -0.0002

Data Index: 1607851 (Python Code)

Max Activating Token Index: 21

Text #4

Max Range: 6.8545. Min Range: -6.8545

Max Act: 6.6327. Min Act: -0.0002

Data Index: 1378637 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 6.8545. Min Range: -6.8545

Max Act: 6.4414. Min Act: -0.0002

Data Index: 1501961 (Python Code)

Max Activating Token Index: 17

Text #6

Max Range: 6.8545. Min Range: -6.8545

Max Act: 6.2866. Min Act: -0.0002

Data Index: 1604534 (Python Code)

Max Activating Token Index: 23

Text #7

Max Range: 6.8545. Min Range: -6.8545

Max Act: 6.1906. Min Act: -0.0002

Data Index: 1361406 (Python Code)

Max Activating Token Index: 25

Text #8

Max Range: 6.8545. Min Range: -6.8545

Max Act: 5.9868. Min Act: -0.0002

Data Index: 1499223 (Python Code)

Max Activating Token Index: 18

Text #9

Max Range: 6.8545. Min Range: -6.8545

Max Act: 5.9587. Min Act: -0.0002

Data Index: 1552992 (Python Code)

Max Activating Token Index: 18

Text #10

Max Range: 6.8545. Min Range: -6.8545

Max Act: 5.9713. Min Act: -0.0002

Data Index: 1509639 (Python Code)

Max Activating Token Index: 241

Text #11

Max Range: 6.8545. Min Range: -6.8545

Max Act: 5.9195. Min Act: -0.0002

Data Index: 1446160 (Python Code)

Max Activating Token Index: 17

Text #12

Max Range: 6.8545. Min Range: -6.8545

Max Act: 6.0017. Min Act: -0.0002

Data Index: 1453179 (Python Code)

Max Activating Token Index: 30

Text #13

Max Range: 6.8545. Min Range: -6.8545

Max Act: 5.9995. Min Act: -0.0002

Data Index: 1595014 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 6.8545. Min Range: -6.8545

Max Act: 5.9145. Min Act: -0.0002

Data Index: 1488538 (Python Code)

Max Activating Token Index: 20

Text #15

Max Range: 6.8545. Min Range: -6.8545

Max Act: 5.9386. Min Act: -0.0002

Data Index: 1559807 (Python Code)

Max Activating Token Index: 22

Text #16

Max Range: 6.8545. Min Range: -6.8545

Max Act: 5.8288. Min Act: -0.0002

Data Index: 1522287 (Python Code)

Max Activating Token Index: 11

Text #17

Max Range: 6.8545. Min Range: -6.8545

Max Act: 5.7525. Min Act: -0.0002

Data Index: 1512268 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 6.8545. Min Range: -6.8545

Max Act: 5.8211. Min Act: -0.0002

Data Index: 1572397 (Python Code)

Max Activating Token Index: 30

Text #19

Max Range: 6.8545. Min Range: -6.8545

Max Act: 5.7409. Min Act: -0.0002

Data Index: 1389300 (Python Code)

Max Activating Token Index: 12