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

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

Neuron 3751 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0659. Min Range: -1.0659

Max Act: 1.0659. Min Act: -0.0000

Data Index: 442493 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.9055. Min Act: -0.0000

Data Index: 561019 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1156227 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8651. Min Act: -0.0000

Data Index: 479236 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8469. Min Act: -0.0000

Data Index: 299322 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8857. Min Act: -0.0000

Data Index: 888558 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8737. Min Act: -0.0000

Data Index: 1195738 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8792. Min Act: -0.0000

Data Index: 1281547 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8788. Min Act: -0.0000

Data Index: 809357 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8744. Min Act: -0.0000

Data Index: 227681 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8669. Min Act: -0.0000

Data Index: 350067 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8699. Min Act: -0.0000

Data Index: 398159 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8613. Min Act: -0.0000

Data Index: 1172 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8552. Min Act: -0.0000

Data Index: 614890 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8443. Min Act: -0.0000

Data Index: 353397 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8424. Min Act: -0.0000

Data Index: 311045 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8703. Min Act: -0.0000

Data Index: 14952 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8203. Min Act: -0.0000

Data Index: 1034481 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.7701. Min Act: -0.0000

Data Index: 65443 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 1.0659. Min Range: -1.0659

Max Act: 0.8574. Min Act: -0.0000

Data Index: 303957 (C4 (Web Text))

Max Activating Token Index: 678