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

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

Neuron 3119 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: 0.0642. Min Range: -0.0642

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1141547 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0632. Min Act: -0.0002

Data Index: 917725 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0619. Min Act: -0.0002

Data Index: 162768 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1365310 (Python Code)

Max Activating Token Index: 443

Text #4

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1213078 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0599. Min Act: -0.0002

Data Index: 93232 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1374675 (Python Code)

Max Activating Token Index: 472

Text #7

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1235028 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0577. Min Act: -0.0002

Data Index: 433223 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1012879 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0579. Min Act: -0.0002

Data Index: 818188 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0574. Min Act: -0.0002

Data Index: 119082 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1316716 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0568. Min Act: -0.0002

Data Index: 45875 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1477620 (Python Code)

Max Activating Token Index: 270

Text #15

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0563. Min Act: -0.0002

Data Index: 371432 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0572. Min Act: -0.0002

Data Index: 839850 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1257607 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1274956 (C4 (Web Text))

Max Activating Token Index: 7

Text #19

Max Range: 0.0642. Min Range: -0.0642

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1541199 (Python Code)

Max Activating Token Index: 427