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

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

Neuron 3644 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3518. Min Range: -2.3518

Max Act: 2.3518. Min Act: -0.0000

Data Index: 1504985 (Python Code)

Max Activating Token Index: 362

Text #1

Max Range: 2.3518. Min Range: -2.3518

Max Act: 1.9899. Min Act: -0.0000

Data Index: 1579595 (Python Code)

Max Activating Token Index: 284

Text #2

Max Range: 2.3518. Min Range: -2.3518

Max Act: 1.9632. Min Act: -0.0000

Data Index: 1541948 (Python Code)

Max Activating Token Index: 446

Text #3

Max Range: 2.3518. Min Range: -2.3518

Max Act: 2.0639. Min Act: -0.0000

Data Index: 86538 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 2.3518. Min Range: -2.3518

Max Act: 2.0295. Min Act: -0.0000

Data Index: 1456349 (Python Code)

Max Activating Token Index: 480

Text #5

Max Range: 2.3518. Min Range: -2.3518

Max Act: 1.9597. Min Act: -0.0000

Data Index: 463028 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 2.3518. Min Range: -2.3518

Max Act: 1.6955. Min Act: 0.0000

Data Index: 420240 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 2.3518. Min Range: -2.3518

Max Act: 1.6835. Min Act: -0.0000

Data Index: 941610 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 2.3518. Min Range: -2.3518

Max Act: 1.6464. Min Act: -0.0000

Data Index: 547691 (C4 (Web Text))

Max Activating Token Index: 982

Text #9

Max Range: 2.3518. Min Range: -2.3518

Max Act: 1.6364. Min Act: -0.0000

Data Index: 894042 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 2.3518. Min Range: -2.3518

Max Act: 1.5267. Min Act: -0.0000

Data Index: 540221 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 2.3518. Min Range: -2.3518

Max Act: 1.7173. Min Act: -0.0000

Data Index: 540369 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 2.3518. Min Range: -2.3518

Max Act: 1.6560. Min Act: -0.0000

Data Index: 1145696 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 2.3518. Min Range: -2.3518

Max Act: 1.7460. Min Act: -0.0000

Data Index: 1531856 (Python Code)

Max Activating Token Index: 133

Text #14

Max Range: 2.3518. Min Range: -2.3518

Max Act: 1.6523. Min Act: -0.0000

Data Index: 314792 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 2.3518. Min Range: -2.3518

Max Act: 1.6266. Min Act: 0.0000

Data Index: 437604 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 2.3518. Min Range: -2.3518

Max Act: 1.6216. Min Act: -0.0000

Data Index: 556458 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 2.3518. Min Range: -2.3518

Max Act: 1.5967. Min Act: -0.0000

Data Index: 1041583 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 2.3518. Min Range: -2.3518

Max Act: 1.4909. Min Act: -0.0000

Data Index: 1070318 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 2.3518. Min Range: -2.3518

Max Act: 1.5017. Min Act: -0.0000

Data Index: 1028614 (C4 (Web Text))

Max Activating Token Index: 193