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

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

Neuron 547 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3581. Min Range: -2.3581

Max Act: 2.3051. Min Act: -0.0000

Data Index: 36639 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 2.3581. Min Range: -2.3581

Max Act: 2.2864. Min Act: -0.0000

Data Index: 499275 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 2.3581. Min Range: -2.3581

Max Act: 2.3581. Min Act: -0.0000

Data Index: 247029 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 2.3581. Min Range: -2.3581

Max Act: 2.2258. Min Act: -0.0001

Data Index: 1595298 (Python Code)

Max Activating Token Index: 530

Text #4

Max Range: 2.3581. Min Range: -2.3581

Max Act: 2.2190. Min Act: -0.0000

Data Index: 1570739 (Python Code)

Max Activating Token Index: 807

Text #5

Max Range: 2.3581. Min Range: -2.3581

Max Act: 2.2096. Min Act: -0.0000

Data Index: 1621188 (Python Code)

Max Activating Token Index: 756

Text #6

Max Range: 2.3581. Min Range: -2.3581

Max Act: 2.1480. Min Act: -0.0000

Data Index: 1145475 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 2.3581. Min Range: -2.3581

Max Act: 2.1170. Min Act: -0.0000

Data Index: 649696 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 2.3581. Min Range: -2.3581

Max Act: 2.0823. Min Act: -0.0000

Data Index: 953423 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 2.3581. Min Range: -2.3581

Max Act: 2.2315. Min Act: -0.0000

Data Index: 608481 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 2.3581. Min Range: -2.3581

Max Act: 1.9224. Min Act: -0.0001

Data Index: 624689 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 2.3581. Min Range: -2.3581

Max Act: 2.1486. Min Act: -0.0000

Data Index: 1012361 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 2.3581. Min Range: -2.3581

Max Act: 2.0412. Min Act: -0.0000

Data Index: 494710 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 2.3581. Min Range: -2.3581

Max Act: 2.0078. Min Act: -0.0000

Data Index: 267912 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 2.3581. Min Range: -2.3581

Max Act: 2.1164. Min Act: -0.0001

Data Index: 1533592 (Python Code)

Max Activating Token Index: 312

Text #15

Max Range: 2.3581. Min Range: -2.3581

Max Act: 1.8908. Min Act: -0.0000

Data Index: 1462517 (Python Code)

Max Activating Token Index: 439

Text #16

Max Range: 2.3581. Min Range: -2.3581

Max Act: 1.7975. Min Act: -0.0000

Data Index: 526000 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 2.3581. Min Range: -2.3581

Max Act: 1.8852. Min Act: -0.0001

Data Index: 1453600 (Python Code)

Max Activating Token Index: 806

Text #18

Max Range: 2.3581. Min Range: -2.3581

Max Act: 1.8310. Min Act: -0.0000

Data Index: 1539292 (Python Code)

Max Activating Token Index: 475

Text #19

Max Range: 2.3581. Min Range: -2.3581

Max Act: 1.9917. Min Act: -0.0000

Data Index: 491923 (C4 (Web Text))

Max Activating Token Index: 285