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

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

Neuron 1551 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.8342. Min Act: -0.0000

Data Index: 635077 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.8334. Min Act: -0.0000

Data Index: 848604 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.6563. Min Act: -0.0000

Data Index: 974780 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.5356. Min Act: -0.0000

Data Index: 42130 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.5701. Min Act: -0.0000

Data Index: 965951 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1358176 (C4 (Web Text))

Max Activating Token Index: 115

Text #6

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4812. Min Act: -0.0000

Data Index: 133312 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1215599 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4286. Min Act: -0.0000

Data Index: 25062 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4429. Min Act: -0.0000

Data Index: 201048 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4350. Min Act: -0.0000

Data Index: 596345 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4301. Min Act: -0.0000

Data Index: 821382 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4447. Min Act: -0.0000

Data Index: 90280 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4285. Min Act: -0.0000

Data Index: 33977 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.3892. Min Act: -0.0000

Data Index: 1263227 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.3394. Min Act: -0.0000

Data Index: 425614 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.3765. Min Act: -0.0000

Data Index: 262326 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.3846. Min Act: -0.0000

Data Index: 130235 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.4261. Min Act: -0.0000

Data Index: 4924 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.8342. Min Range: -0.8342

Max Act: 0.3474. Min Act: -0.0000

Data Index: 983249 (C4 (Web Text))

Max Activating Token Index: 129