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

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

Neuron 378 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0702. Min Act: -0.0002

Data Index: 12 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0584. Min Act: -0.0002

Data Index: 451085 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1280594 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0567. Min Act: -0.0002

Data Index: 925935 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0589. Min Act: -0.0002

Data Index: 590647 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1015599 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1180612 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1135726 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0568. Min Act: -0.0002

Data Index: 892727 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1120573 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1330342 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0575. Min Act: -0.0002

Data Index: 25466 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0548. Min Act: -0.0002

Data Index: 689920 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1025481 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0536. Min Act: -0.0002

Data Index: 3317 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0520. Min Act: -0.0002

Data Index: 598600 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0546. Min Act: -0.0002

Data Index: 550673 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1300538 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0535. Min Act: -0.0002

Data Index: 92129 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0534. Min Act: -0.0002

Data Index: 258989 (C4 (Web Text))

Max Activating Token Index: 111