Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 313 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0674. Min Act: -0.0001

Data Index: 1437038 (Python Code)

Max Activating Token Index: 503

Text #1

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0706. Min Act: -0.0001

Data Index: 1422821 (Python Code)

Max Activating Token Index: 967

Text #2

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1518540 (Python Code)

Max Activating Token Index: 207

Text #3

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0531. Min Act: -0.0000

Data Index: 35126 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0553. Min Act: -0.0000

Data Index: 904968 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1598907 (Python Code)

Max Activating Token Index: 314

Text #6

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0536. Min Act: -0.0001

Data Index: 1052857 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0501. Min Act: -0.0000

Data Index: 597035 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0521. Min Act: -0.0000

Data Index: 1025861 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0522. Min Act: -0.0001

Data Index: 237443 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0517. Min Act: -0.0000

Data Index: 797860 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0475. Min Act: -0.0001

Data Index: 1508316 (Python Code)

Max Activating Token Index: 648

Text #12

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1335609 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0500. Min Act: -0.0001

Data Index: 1377573 (Python Code)

Max Activating Token Index: 574

Text #14

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0478. Min Act: -0.0001

Data Index: 681036 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0488. Min Act: -0.0000

Data Index: 338246 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0499. Min Act: -0.0001

Data Index: 1553880 (Python Code)

Max Activating Token Index: 492

Text #17

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0484. Min Act: -0.0000

Data Index: 1136620 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0471. Min Act: -0.0000

Data Index: 808188 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 0.0706. Min Range: -0.0706

Max Act: 0.0471. Min Act: -0.0000

Data Index: 1357712 (C4 (Web Text))

Max Activating Token Index: 482