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

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

Neuron 3206 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9370. Min Range: -2.9370

Max Act: 2.9370. Min Act: -0.0000

Data Index: 508206 (C4 (Web Text))

Max Activating Token Index: 200

Text #1

Max Range: 2.9370. Min Range: -2.9370

Max Act: 2.6772. Min Act: -0.0000

Data Index: 156239 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 2.9370. Min Range: -2.9370

Max Act: 2.8421. Min Act: -0.0000

Data Index: 269826 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 2.9370. Min Range: -2.9370

Max Act: 2.4486. Min Act: -0.0000

Data Index: 162342 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 2.9370. Min Range: -2.9370

Max Act: 2.2587. Min Act: -0.0001

Data Index: 471528 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 2.9370. Min Range: -2.9370

Max Act: 2.1801. Min Act: -0.0000

Data Index: 1084094 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 2.9370. Min Range: -2.9370

Max Act: 2.2207. Min Act: -0.0000

Data Index: 1161573 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 2.9370. Min Range: -2.9370

Max Act: 2.2381. Min Act: -0.0000

Data Index: 174337 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 2.9370. Min Range: -2.9370

Max Act: 2.2913. Min Act: -0.0001

Data Index: 1043133 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 2.9370. Min Range: -2.9370

Max Act: 2.1999. Min Act: -0.0000

Data Index: 1100646 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 2.9370. Min Range: -2.9370

Max Act: 1.8746. Min Act: -0.0001

Data Index: 739458 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 2.9370. Min Range: -2.9370

Max Act: 2.2289. Min Act: -0.0000

Data Index: 1362003 (Python Code)

Max Activating Token Index: 556

Text #12

Max Range: 2.9370. Min Range: -2.9370

Max Act: 2.2087. Min Act: -0.0000

Data Index: 564631 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 2.9370. Min Range: -2.9370

Max Act: 2.3169. Min Act: -0.0000

Data Index: 1033696 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 2.9370. Min Range: -2.9370

Max Act: 2.0644. Min Act: -0.0001

Data Index: 1284513 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 2.9370. Min Range: -2.9370

Max Act: 2.2562. Min Act: -0.0001

Data Index: 1279121 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 2.9370. Min Range: -2.9370

Max Act: 2.1257. Min Act: -0.0000

Data Index: 110529 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 2.9370. Min Range: -2.9370

Max Act: 2.2187. Min Act: -0.0000

Data Index: 90868 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 2.9370. Min Range: -2.9370

Max Act: 2.1344. Min Act: -0.0000

Data Index: 1578799 (Python Code)

Max Activating Token Index: 549

Text #19

Max Range: 2.9370. Min Range: -2.9370

Max Act: 2.1002. Min Act: -0.0000

Data Index: 1024480 (C4 (Web Text))

Max Activating Token Index: 703