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

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

Neuron 1000 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: 0.0532. Min Range: -0.0532

Max Act: 0.0532. Min Act: -0.0002

Data Index: 285629 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0518. Min Act: -0.0002

Data Index: 834122 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1252196 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1334193 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0493. Min Act: -0.0002

Data Index: 702519 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1240000 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0466. Min Act: -0.0002

Data Index: 673796 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0433. Min Act: -0.0002

Data Index: 756491 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1205148 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0456. Min Act: -0.0002

Data Index: 42020 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1349954 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0431. Min Act: -0.0002

Data Index: 777787 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0406. Min Act: -0.0002

Data Index: 590767 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1103892 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0432. Min Act: -0.0002

Data Index: 245028 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1050133 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0438. Min Act: -0.0002

Data Index: 544783 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1291652 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0419. Min Act: -0.0002

Data Index: 954264 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0427. Min Act: -0.0002

Data Index: 576358 (C4 (Web Text))

Max Activating Token Index: 740