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

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

Neuron 2079 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.8138. Min Act: -0.0000

Data Index: 1421697 (Python Code)

Max Activating Token Index: 274

Text #1

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.6090. Min Act: -0.0000

Data Index: 1409513 (Python Code)

Max Activating Token Index: 549

Text #2

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.0916. Min Act: -0.0000

Data Index: 1548657 (Python Code)

Max Activating Token Index: 777

Text #3

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.3932. Min Act: -0.0000

Data Index: 1524267 (Python Code)

Max Activating Token Index: 378

Text #4

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.1031. Min Act: -0.0000

Data Index: 1388422 (Python Code)

Max Activating Token Index: 96

Text #5

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.0656. Min Act: -0.0000

Data Index: 1473136 (Python Code)

Max Activating Token Index: 550

Text #6

Max Range: 2.8138. Min Range: -2.8138

Max Act: 1.8494. Min Act: -0.0000

Data Index: 1403204 (Python Code)

Max Activating Token Index: 314

Text #7

Max Range: 2.8138. Min Range: -2.8138

Max Act: 1.9611. Min Act: -0.0000

Data Index: 1535328 (Python Code)

Max Activating Token Index: 358

Text #8

Max Range: 2.8138. Min Range: -2.8138

Max Act: 1.9972. Min Act: -0.0000

Data Index: 1457432 (Python Code)

Max Activating Token Index: 646

Text #9

Max Range: 2.8138. Min Range: -2.8138

Max Act: 2.0222. Min Act: -0.0000

Data Index: 1430418 (Python Code)

Max Activating Token Index: 48

Text #10

Max Range: 2.8138. Min Range: -2.8138

Max Act: 1.8303. Min Act: -0.0000

Data Index: 1627330 (Python Code)

Max Activating Token Index: 358

Text #11

Max Range: 2.8138. Min Range: -2.8138

Max Act: 1.8120. Min Act: -0.0000

Data Index: 1396076 (Python Code)

Max Activating Token Index: 484

Text #12

Max Range: 2.8138. Min Range: -2.8138

Max Act: 1.7548. Min Act: -0.0000

Data Index: 1652160 (Python Code)

Max Activating Token Index: 118

Text #13

Max Range: 2.8138. Min Range: -2.8138

Max Act: 1.7907. Min Act: -0.0000

Data Index: 1603864 (Python Code)

Max Activating Token Index: 499

Text #14

Max Range: 2.8138. Min Range: -2.8138

Max Act: 1.7919. Min Act: -0.0000

Data Index: 1518862 (Python Code)

Max Activating Token Index: 50

Text #15

Max Range: 2.8138. Min Range: -2.8138

Max Act: 1.4917. Min Act: -0.0000

Data Index: 1650663 (Python Code)

Max Activating Token Index: 583

Text #16

Max Range: 2.8138. Min Range: -2.8138

Max Act: 1.4793. Min Act: -0.0000

Data Index: 1642184 (Python Code)

Max Activating Token Index: 416

Text #17

Max Range: 2.8138. Min Range: -2.8138

Max Act: 1.4500. Min Act: -0.0000

Data Index: 1445469 (Python Code)

Max Activating Token Index: 437

Text #18

Max Range: 2.8138. Min Range: -2.8138

Max Act: 1.6113. Min Act: -0.0000

Data Index: 1590337 (Python Code)

Max Activating Token Index: 723

Text #19

Max Range: 2.8138. Min Range: -2.8138

Max Act: 1.5925. Min Act: -0.0000

Data Index: 1569031 (Python Code)

Max Activating Token Index: 249