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

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

Neuron 2340 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: 0.0671. Min Range: -0.0671

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1144224 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1439685 (Python Code)

Max Activating Token Index: 673

Text #2

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1395461 (Python Code)

Max Activating Token Index: 544

Text #3

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1539005 (Python Code)

Max Activating Token Index: 696

Text #4

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1429710 (Python Code)

Max Activating Token Index: 682

Text #5

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0592. Min Act: -0.0002

Data Index: 120266 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1655317 (Python Code)

Max Activating Token Index: 59

Text #7

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1502611 (Python Code)

Max Activating Token Index: 778

Text #8

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1528289 (Python Code)

Max Activating Token Index: 593

Text #9

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0588. Min Act: -0.0002

Data Index: 596704 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0555. Min Act: -0.0003

Data Index: 673946 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0553. Min Act: -0.0002

Data Index: 322989 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1418843 (Python Code)

Max Activating Token Index: 140

Text #13

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1619128 (Python Code)

Max Activating Token Index: 306

Text #14

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1482596 (Python Code)

Max Activating Token Index: 152

Text #15

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1651056 (Python Code)

Max Activating Token Index: 32

Text #16

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1414128 (Python Code)

Max Activating Token Index: 654

Text #17

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1648017 (Python Code)

Max Activating Token Index: 901

Text #18

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1488869 (Python Code)

Max Activating Token Index: 775

Text #19

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0535. Min Act: -0.0002

Data Index: 817213 (C4 (Web Text))

Max Activating Token Index: 146