Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1992 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.6517. Min Act: -0.0003

Data Index: 1295537 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5135. Min Act: -0.0002

Data Index: 862397 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5049. Min Act: -0.0002

Data Index: 1512314 (Python Code)

Max Activating Token Index: 260

Text #3

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4733. Min Act: -0.0002

Data Index: 1646521 (Python Code)

Max Activating Token Index: 690

Text #4

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4642. Min Act: -0.0002

Data Index: 1458450 (Python Code)

Max Activating Token Index: 919

Text #5

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4579. Min Act: -0.0002

Data Index: 1404476 (Python Code)

Max Activating Token Index: 716

Text #6

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4526. Min Act: -0.0002

Data Index: 1650157 (Python Code)

Max Activating Token Index: 680

Text #7

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4505. Min Act: -0.0002

Data Index: 1491913 (Python Code)

Max Activating Token Index: 628

Text #8

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4469. Min Act: -0.0002

Data Index: 1614826 (Python Code)

Max Activating Token Index: 429

Text #9

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4342. Min Act: -0.0002

Data Index: 1366450 (Python Code)

Max Activating Token Index: 177

Text #10

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4312. Min Act: -0.0002

Data Index: 1429281 (Python Code)

Max Activating Token Index: 436

Text #11

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4290. Min Act: -0.0002

Data Index: 1652278 (Python Code)

Max Activating Token Index: 333

Text #12

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4289. Min Act: -0.0002

Data Index: 1398245 (Python Code)

Max Activating Token Index: 311

Text #13

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4115. Min Act: -0.0002

Data Index: 1481509 (Python Code)

Max Activating Token Index: 42

Text #14

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4243. Min Act: -0.0002

Data Index: 1558724 (Python Code)

Max Activating Token Index: 210

Text #15

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4048. Min Act: -0.0002

Data Index: 467515 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4171. Min Act: -0.0002

Data Index: 1640089 (Python Code)

Max Activating Token Index: 908

Text #17

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4165. Min Act: -0.0003

Data Index: 1197420 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4149. Min Act: -0.0002

Data Index: 1619360 (Python Code)

Max Activating Token Index: 486

Text #19

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4004. Min Act: -0.0002

Data Index: 1513573 (Python Code)

Max Activating Token Index: 396