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

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

Neuron 1513 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1555. Min Range: -3.1555

Max Act: 3.1555. Min Act: -0.0000

Data Index: 1270333 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 3.1555. Min Range: -3.1555

Max Act: 2.6890. Min Act: -0.0000

Data Index: 994906 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 3.1555. Min Range: -3.1555

Max Act: 2.3252. Min Act: -0.0000

Data Index: 296352 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 3.1555. Min Range: -3.1555

Max Act: 2.4495. Min Act: -0.0000

Data Index: 852153 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 3.1555. Min Range: -3.1555

Max Act: 2.3967. Min Act: -0.0000

Data Index: 1176292 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 3.1555. Min Range: -3.1555

Max Act: 2.3693. Min Act: -0.0000

Data Index: 192294 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 3.1555. Min Range: -3.1555

Max Act: 2.2653. Min Act: -0.0000

Data Index: 1057533 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 3.1555. Min Range: -3.1555

Max Act: 2.1361. Min Act: -0.0000

Data Index: 1287739 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 3.1555. Min Range: -3.1555

Max Act: 2.0529. Min Act: -0.0000

Data Index: 1300717 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 3.1555. Min Range: -3.1555

Max Act: 1.9255. Min Act: -0.0000

Data Index: 1605422 (Python Code)

Max Activating Token Index: 1015

Text #10

Max Range: 3.1555. Min Range: -3.1555

Max Act: 2.1444. Min Act: -0.0000

Data Index: 27667 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 3.1555. Min Range: -3.1555

Max Act: 1.9075. Min Act: -0.0000

Data Index: 1501720 (Python Code)

Max Activating Token Index: 773

Text #12

Max Range: 3.1555. Min Range: -3.1555

Max Act: 1.9891. Min Act: -0.0000

Data Index: 323560 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 3.1555. Min Range: -3.1555

Max Act: 1.9465. Min Act: -0.0000

Data Index: 1445934 (Python Code)

Max Activating Token Index: 684

Text #14

Max Range: 3.1555. Min Range: -3.1555

Max Act: 1.9397. Min Act: -0.0000

Data Index: 85118 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 3.1555. Min Range: -3.1555

Max Act: 1.8225. Min Act: -0.0000

Data Index: 273491 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 3.1555. Min Range: -3.1555

Max Act: 2.0128. Min Act: -0.0000

Data Index: 687199 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 3.1555. Min Range: -3.1555

Max Act: 1.8625. Min Act: -0.0000

Data Index: 854357 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 3.1555. Min Range: -3.1555

Max Act: 1.7593. Min Act: -0.0000

Data Index: 93123 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 3.1555. Min Range: -3.1555

Max Act: 1.7509. Min Act: -0.0000

Data Index: 893716 (C4 (Web Text))

Max Activating Token Index: 788