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

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

Neuron 348 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: 4.5520. Min Range: -4.5520

Max Act: 4.5520. Min Act: -0.0000

Data Index: 218353 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 4.5520. Min Range: -4.5520

Max Act: 4.3122. Min Act: -0.0000

Data Index: 1109952 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 4.5520. Min Range: -4.5520

Max Act: 3.6115. Min Act: -0.0000

Data Index: 1527416 (Python Code)

Max Activating Token Index: 867

Text #3

Max Range: 4.5520. Min Range: -4.5520

Max Act: 3.8624. Min Act: -0.0000

Data Index: 1632828 (Python Code)

Max Activating Token Index: 272

Text #4

Max Range: 4.5520. Min Range: -4.5520

Max Act: 3.4986. Min Act: -0.0000

Data Index: 1645195 (Python Code)

Max Activating Token Index: 103

Text #5

Max Range: 4.5520. Min Range: -4.5520

Max Act: 3.7890. Min Act: -0.0000

Data Index: 1625570 (Python Code)

Max Activating Token Index: 977

Text #6

Max Range: 4.5520. Min Range: -4.5520

Max Act: 3.4482. Min Act: -0.0000

Data Index: 1430306 (Python Code)

Max Activating Token Index: 292

Text #7

Max Range: 4.5520. Min Range: -4.5520

Max Act: 3.4205. Min Act: -0.0000

Data Index: 1585770 (Python Code)

Max Activating Token Index: 383

Text #8

Max Range: 4.5520. Min Range: -4.5520

Max Act: 3.4099. Min Act: -0.0000

Data Index: 1548422 (Python Code)

Max Activating Token Index: 377

Text #9

Max Range: 4.5520. Min Range: -4.5520

Max Act: 3.5438. Min Act: -0.0000

Data Index: 1538391 (Python Code)

Max Activating Token Index: 124

Text #10

Max Range: 4.5520. Min Range: -4.5520

Max Act: 2.9973. Min Act: -0.0000

Data Index: 1584556 (Python Code)

Max Activating Token Index: 910

Text #11

Max Range: 4.5520. Min Range: -4.5520

Max Act: 3.6161. Min Act: -0.0000

Data Index: 480149 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 4.5520. Min Range: -4.5520

Max Act: 3.2369. Min Act: -0.0000

Data Index: 1545997 (Python Code)

Max Activating Token Index: 756

Text #13

Max Range: 4.5520. Min Range: -4.5520

Max Act: 3.2698. Min Act: -0.0000

Data Index: 1503502 (Python Code)

Max Activating Token Index: 913

Text #14

Max Range: 4.5520. Min Range: -4.5520

Max Act: 3.5536. Min Act: -0.0000

Data Index: 1460599 (Python Code)

Max Activating Token Index: 905

Text #15

Max Range: 4.5520. Min Range: -4.5520

Max Act: 3.3760. Min Act: -0.0000

Data Index: 316338 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 4.5520. Min Range: -4.5520

Max Act: 3.1846. Min Act: -0.0000

Data Index: 1546446 (Python Code)

Max Activating Token Index: 952

Text #17

Max Range: 4.5520. Min Range: -4.5520

Max Act: 3.1297. Min Act: -0.0000

Data Index: 1422349 (Python Code)

Max Activating Token Index: 178

Text #18

Max Range: 4.5520. Min Range: -4.5520

Max Act: 2.8111. Min Act: -0.0000

Data Index: 1370511 (Python Code)

Max Activating Token Index: 1016

Text #19

Max Range: 4.5520. Min Range: -4.5520

Max Act: 3.0378. Min Act: -0.0000

Data Index: 1516548 (Python Code)

Max Activating Token Index: 700