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

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

Neuron 1104 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: 0.0833. Min Range: -0.0833

Max Act: 0.0833. Min Act: -0.0002

Data Index: 529992 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1077390 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1252078 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0665. Min Act: -0.0002

Data Index: 107436 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0669. Min Act: -0.0002

Data Index: 612666 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0641. Min Act: -0.0002

Data Index: 282101 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0656. Min Act: -0.0002

Data Index: 120642 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0624. Min Act: -0.0002

Data Index: 271141 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0621. Min Act: -0.0002

Data Index: 579802 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0632. Min Act: -0.0002

Data Index: 816631 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0602. Min Act: -0.0003

Data Index: 641152 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0612. Min Act: -0.0002

Data Index: 741673 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0591. Min Act: -0.0002

Data Index: 69897 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0595. Min Act: -0.0002

Data Index: 404883 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1023322 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1075979 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0579. Min Act: -0.0002

Data Index: 757960 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0577. Min Act: -0.0002

Data Index: 921959 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0573. Min Act: -0.0002

Data Index: 336372 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.0833. Min Range: -0.0833

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1089679 (C4 (Web Text))

Max Activating Token Index: 582