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

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

Neuron 5559 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.7605. Min Act: -0.0000

Data Index: 113617 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.6945. Min Act: -0.0000

Data Index: 726705 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.6304. Min Act: -0.0000

Data Index: 80582 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1162404 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.5370. Min Act: -0.0000

Data Index: 990793 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1137524 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.4702. Min Act: -0.0000

Data Index: 1299570 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.5395. Min Act: -0.0000

Data Index: 246046 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.5010. Min Act: -0.0000

Data Index: 696392 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.4880. Min Act: -0.0000

Data Index: 20200 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1015057 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.4603. Min Act: -0.0000

Data Index: 795085 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.4372. Min Act: -0.0000

Data Index: 271832 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1279399 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.4540. Min Act: -0.0000

Data Index: 638944 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.4693. Min Act: -0.0000

Data Index: 275063 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.4742. Min Act: -0.0000

Data Index: 742766 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.4371. Min Act: -0.0000

Data Index: 849079 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.4424. Min Act: -0.0000

Data Index: 1196637 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.7605. Min Range: -0.7605

Max Act: 0.4395. Min Act: -0.0000

Data Index: 331125 (C4 (Web Text))

Max Activating Token Index: 290