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

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

Neuron 5875 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: 0.0625. Min Range: -0.0625

Max Act: 0.0625. Min Act: -0.0002

Data Index: 866605 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0584. Min Act: -0.0002

Data Index: 786221 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0567. Min Act: -0.0002

Data Index: 433191 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0600. Min Act: -0.0002

Data Index: 774885 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0543. Min Act: -0.0002

Data Index: 852982 (C4 (Web Text))

Max Activating Token Index: 143

Text #5

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0523. Min Act: -0.0002

Data Index: 989660 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0513. Min Act: -0.0002

Data Index: 296744 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0509. Min Act: -0.0002

Data Index: 298771 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0506. Min Act: -0.0002

Data Index: 649558 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0481. Min Act: -0.0002

Data Index: 795700 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0496. Min Act: -0.0002

Data Index: 905947 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0475. Min Act: -0.0002

Data Index: 2923 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0503. Min Act: -0.0002

Data Index: 155987 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0467. Min Act: -0.0002

Data Index: 276803 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0474. Min Act: -0.0002

Data Index: 290135 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0477. Min Act: -0.0002

Data Index: 466125 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0473. Min Act: -0.0002

Data Index: 950495 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0451. Min Act: -0.0002

Data Index: 626756 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0469. Min Act: -0.0002

Data Index: 947441 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.0625. Min Range: -0.0625

Max Act: 0.0433. Min Act: -0.0002

Data Index: 578265 (C4 (Web Text))

Max Activating Token Index: 286