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

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

Neuron 5081 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.9438. Min Act: -0.0000

Data Index: 496670 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8134. Min Act: -0.0000

Data Index: 943487 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.8493. Min Act: -0.0000

Data Index: 740570 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7825. Min Act: -0.0000

Data Index: 1326963 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7948. Min Act: -0.0000

Data Index: 202476 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7701. Min Act: -0.0000

Data Index: 835841 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7787. Min Act: -0.0000

Data Index: 159364 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7454. Min Act: -0.0000

Data Index: 1250656 (C4 (Web Text))

Max Activating Token Index: 455

Text #8

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7457. Min Act: -0.0000

Data Index: 1059761 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7453. Min Act: -0.0000

Data Index: 411361 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.7263. Min Act: -0.0000

Data Index: 770773 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.5552. Min Act: -0.0000

Data Index: 136767 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.5876. Min Act: -0.0000

Data Index: 1561476 (Python Code)

Max Activating Token Index: 105

Text #13

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1530638 (Python Code)

Max Activating Token Index: 643

Text #14

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.5609. Min Act: -0.0000

Data Index: 759687 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.5673. Min Act: -0.0000

Data Index: 534407 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1430787 (Python Code)

Max Activating Token Index: 636

Text #17

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1432242 (Python Code)

Max Activating Token Index: 303

Text #18

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.5169. Min Act: -0.0000

Data Index: 338106 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.9438. Min Range: -0.9438

Max Act: 0.5889. Min Act: -0.0000

Data Index: 1116631 (C4 (Web Text))

Max Activating Token Index: 714