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

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

Neuron 59 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: 2.1586. Min Range: -2.1586

Max Act: 2.1548. Min Act: -0.0000

Data Index: 217152 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 2.1586. Min Range: -2.1586

Max Act: 2.1586. Min Act: -0.0000

Data Index: 297699 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 2.1586. Min Range: -2.1586

Max Act: 1.8786. Min Act: -0.0000

Data Index: 792309 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 2.1586. Min Range: -2.1586

Max Act: 1.7986. Min Act: 0.0000

Data Index: 323806 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 2.1586. Min Range: -2.1586

Max Act: 2.0106. Min Act: -0.0000

Data Index: 912520 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 2.1586. Min Range: -2.1586

Max Act: 1.7976. Min Act: -0.0000

Data Index: 76369 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 2.1586. Min Range: -2.1586

Max Act: 1.8747. Min Act: 0.0000

Data Index: 640697 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 2.1586. Min Range: -2.1586

Max Act: 1.6069. Min Act: 0.0000

Data Index: 1258541 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 2.1586. Min Range: -2.1586

Max Act: 1.6889. Min Act: -0.0000

Data Index: 506263 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 2.1586. Min Range: -2.1586

Max Act: 1.5556. Min Act: 0.0000

Data Index: 557865 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 2.1586. Min Range: -2.1586

Max Act: 1.5588. Min Act: -0.0000

Data Index: 753988 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 2.1586. Min Range: -2.1586

Max Act: 1.5238. Min Act: -0.0000

Data Index: 760779 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 2.1586. Min Range: -2.1586

Max Act: 1.6135. Min Act: -0.0000

Data Index: 199237 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 2.1586. Min Range: -2.1586

Max Act: 1.5084. Min Act: -0.0000

Data Index: 1248885 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 2.1586. Min Range: -2.1586

Max Act: 1.4857. Min Act: -0.0000

Data Index: 1121554 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 2.1586. Min Range: -2.1586

Max Act: 1.3963. Min Act: -0.0000

Data Index: 1051695 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 2.1586. Min Range: -2.1586

Max Act: 1.4517. Min Act: -0.0000

Data Index: 844485 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 2.1586. Min Range: -2.1586

Max Act: 1.4375. Min Act: -0.0000

Data Index: 339713 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 2.1586. Min Range: -2.1586

Max Act: 1.3516. Min Act: 0.0000

Data Index: 1253623 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 2.1586. Min Range: -2.1586

Max Act: 1.4386. Min Act: -0.0000

Data Index: 210552 (C4 (Web Text))

Max Activating Token Index: 720