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

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

Neuron 1718 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: 0.0679. Min Range: -0.0679

Max Act: 0.0679. Min Act: -0.0001

Data Index: 815564 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0596. Min Act: -0.0001

Data Index: 87192 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1143798 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0560. Min Act: -0.0002

Data Index: 312000 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1024146 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0539. Min Act: -0.0001

Data Index: 389698 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0518. Min Act: -0.0000

Data Index: 65540 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0514. Min Act: -0.0001

Data Index: 4128 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0520. Min Act: -0.0002

Data Index: 179695 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0510. Min Act: -0.0002

Data Index: 349472 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1061390 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0476. Min Act: -0.0001

Data Index: 462764 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0493. Min Act: -0.0002

Data Index: 482675 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0486. Min Act: -0.0002

Data Index: 126570 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0486. Min Act: -0.0001

Data Index: 461609 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0490. Min Act: -0.0001

Data Index: 623408 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0501. Min Act: -0.0002

Data Index: 687972 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0488. Min Act: -0.0002

Data Index: 473244 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0477. Min Act: -0.0002

Data Index: 64754 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.0679. Min Range: -0.0679

Max Act: 0.0507. Min Act: -0.0001

Data Index: 383031 (C4 (Web Text))

Max Activating Token Index: 345