Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2391 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.4517. Min Range: -4.4517

Max Act: 4.4517. Min Act: -0.0000

Data Index: 512641 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 4.4517. Min Range: -4.4517

Max Act: 4.2502. Min Act: -0.0000

Data Index: 1028618 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 4.4517. Min Range: -4.4517

Max Act: 4.4296. Min Act: -0.0000

Data Index: 444727 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 4.4517. Min Range: -4.4517

Max Act: 4.4497. Min Act: -0.0000

Data Index: 259399 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 4.4517. Min Range: -4.4517

Max Act: 3.9672. Min Act: -0.0000

Data Index: 160394 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 4.4517. Min Range: -4.4517

Max Act: 4.1143. Min Act: -0.0000

Data Index: 313490 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 4.4517. Min Range: -4.4517

Max Act: 3.9479. Min Act: -0.0000

Data Index: 429662 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 4.4517. Min Range: -4.4517

Max Act: 4.0084. Min Act: -0.0000

Data Index: 19530 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 4.4517. Min Range: -4.4517

Max Act: 3.8865. Min Act: -0.0000

Data Index: 277780 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 4.4517. Min Range: -4.4517

Max Act: 4.0077. Min Act: -0.0000

Data Index: 717809 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 4.4517. Min Range: -4.4517

Max Act: 3.8767. Min Act: -0.0000

Data Index: 1341900 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 4.4517. Min Range: -4.4517

Max Act: 3.9933. Min Act: -0.0000

Data Index: 293368 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 4.4517. Min Range: -4.4517

Max Act: 3.7925. Min Act: -0.0000

Data Index: 658371 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 4.4517. Min Range: -4.4517

Max Act: 4.1933. Min Act: -0.0000

Data Index: 58752 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 4.4517. Min Range: -4.4517

Max Act: 4.0080. Min Act: -0.0000

Data Index: 208698 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 4.4517. Min Range: -4.4517

Max Act: 3.7862. Min Act: -0.0000

Data Index: 513586 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 4.4517. Min Range: -4.4517

Max Act: 3.6470. Min Act: -0.0000

Data Index: 879536 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 4.4517. Min Range: -4.4517

Max Act: 3.8270. Min Act: -0.0000

Data Index: 785812 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 4.4517. Min Range: -4.4517

Max Act: 3.7646. Min Act: -0.0000

Data Index: 562108 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 4.4517. Min Range: -4.4517

Max Act: 3.6099. Min Act: -0.0000

Data Index: 33216 (C4 (Web Text))

Max Activating Token Index: 602