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

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

Neuron 2407 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: 1.8407. Min Range: -1.8407

Max Act: 1.8407. Min Act: -0.0000

Data Index: 1596604 (Python Code)

Max Activating Token Index: 1022

Text #1

Max Range: 1.8407. Min Range: -1.8407

Max Act: 1.6913. Min Act: -0.0000

Data Index: 104475 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 1.8407. Min Range: -1.8407

Max Act: 1.7008. Min Act: -0.0000

Data Index: 115512 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 1.8407. Min Range: -1.8407

Max Act: 1.3421. Min Act: -0.0000

Data Index: 1554021 (Python Code)

Max Activating Token Index: 907

Text #4

Max Range: 1.8407. Min Range: -1.8407

Max Act: 1.5420. Min Act: -0.0000

Data Index: 1472868 (Python Code)

Max Activating Token Index: 951

Text #5

Max Range: 1.8407. Min Range: -1.8407

Max Act: 1.4313. Min Act: -0.0000

Data Index: 669351 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 1.8407. Min Range: -1.8407

Max Act: 1.4108. Min Act: -0.0000

Data Index: 1446069 (Python Code)

Max Activating Token Index: 254

Text #7

Max Range: 1.8407. Min Range: -1.8407

Max Act: 1.4632. Min Act: -0.0000

Data Index: 602802 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 1.8407. Min Range: -1.8407

Max Act: 1.3284. Min Act: -0.0000

Data Index: 1572860 (Python Code)

Max Activating Token Index: 172

Text #9

Max Range: 1.8407. Min Range: -1.8407

Max Act: 1.2408. Min Act: -0.0000

Data Index: 1191804 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 1.8407. Min Range: -1.8407

Max Act: 1.4310. Min Act: -0.0000

Data Index: 1572567 (Python Code)

Max Activating Token Index: 655

Text #11

Max Range: 1.8407. Min Range: -1.8407

Max Act: 1.3686. Min Act: -0.0000

Data Index: 582344 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 1.8407. Min Range: -1.8407

Max Act: 1.3255. Min Act: -0.0000

Data Index: 998571 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 1.8407. Min Range: -1.8407

Max Act: 1.2481. Min Act: -0.0000

Data Index: 1439092 (Python Code)

Max Activating Token Index: 608

Text #14

Max Range: 1.8407. Min Range: -1.8407

Max Act: 1.2054. Min Act: -0.0000

Data Index: 1651917 (Python Code)

Max Activating Token Index: 484

Text #15

Max Range: 1.8407. Min Range: -1.8407

Max Act: 1.3111. Min Act: -0.0000

Data Index: 117251 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 1.8407. Min Range: -1.8407

Max Act: 1.2124. Min Act: -0.0000

Data Index: 670198 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 1.8407. Min Range: -1.8407

Max Act: 1.1663. Min Act: -0.0000

Data Index: 1521132 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 1.8407. Min Range: -1.8407

Max Act: 1.1824. Min Act: -0.0000

Data Index: 1018314 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 1.8407. Min Range: -1.8407

Max Act: 1.2206. Min Act: -0.0000

Data Index: 518282 (C4 (Web Text))

Max Activating Token Index: 213