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

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

Neuron 13 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.2894. Min Act: -0.0000

Data Index: 804442 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.5138. Min Act: -0.0000

Data Index: 220314 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.4152. Min Act: -0.0000

Data Index: 1092502 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.4367. Min Act: -0.0000

Data Index: 610733 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.1872. Min Act: -0.0000

Data Index: 1404724 (Python Code)

Max Activating Token Index: 826

Text #5

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.1624. Min Act: -0.0000

Data Index: 1638971 (Python Code)

Max Activating Token Index: 1022

Text #6

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.3444. Min Act: -0.0000

Data Index: 1417709 (Python Code)

Max Activating Token Index: 838

Text #7

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.3507. Min Act: -0.0000

Data Index: 867333 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.2137. Min Act: -0.0000

Data Index: 915046 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.4224. Min Act: -0.0000

Data Index: 689774 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.0286. Min Act: -0.0000

Data Index: 1398708 (Python Code)

Max Activating Token Index: 764

Text #11

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.0095. Min Act: -0.0000

Data Index: 1472247 (Python Code)

Max Activating Token Index: 743

Text #12

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.1270. Min Act: -0.0000

Data Index: 1490304 (Python Code)

Max Activating Token Index: 864

Text #13

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.1230. Min Act: -0.0000

Data Index: 1404854 (Python Code)

Max Activating Token Index: 17

Text #14

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.0213. Min Act: -0.0000

Data Index: 1444236 (Python Code)

Max Activating Token Index: 758

Text #15

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.0994. Min Act: -0.0000

Data Index: 631422 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.0823. Min Act: -0.0000

Data Index: 1579887 (Python Code)

Max Activating Token Index: 962

Text #17

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.1470. Min Act: -0.0000

Data Index: 1618657 (Python Code)

Max Activating Token Index: 1020

Text #18

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.1457. Min Act: -0.0000

Data Index: 1408413 (Python Code)

Max Activating Token Index: 813

Text #19

Max Range: 2.5138. Min Range: -2.5138

Max Act: 2.0544. Min Act: -0.0000

Data Index: 1365836 (Python Code)

Max Activating Token Index: 1012