Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3616 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0716. Min Act: -0.0001

Data Index: 87834 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1337947 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1242951 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0565. Min Act: -0.0001

Data Index: 314514 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0555. Min Act: -0.0002

Data Index: 756652 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0571. Min Act: -0.0001

Data Index: 22413 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0621. Min Act: -0.0002

Data Index: 495258 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0584. Min Act: -0.0002

Data Index: 794908 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1050469 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0578. Min Act: -0.0002

Data Index: 462980 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1202636 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1008131 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0572. Min Act: -0.0001

Data Index: 538516 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0542. Min Act: -0.0001

Data Index: 659684 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0546. Min Act: -0.0001

Data Index: 975092 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0523. Min Act: -0.0002

Data Index: 214941 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0560. Min Act: -0.0002

Data Index: 121498 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0539. Min Act: -0.0001

Data Index: 636188 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0577. Min Act: -0.0001

Data Index: 1065840 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.0716. Min Range: -0.0716

Max Act: 0.0592. Min Act: -0.0002

Data Index: 710625 (C4 (Web Text))

Max Activating Token Index: 606