Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1466 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.7039. Min Act: -0.0000

Data Index: 374955 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.4954. Min Act: -0.0000

Data Index: 512697 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.5485. Min Act: -0.0000

Data Index: 1395512 (Python Code)

Max Activating Token Index: 958

Text #3

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.4247. Min Act: -0.0000

Data Index: 1381163 (Python Code)

Max Activating Token Index: 1020

Text #4

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.3274. Min Act: -0.0000

Data Index: 754006 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.2349. Min Act: -0.0000

Data Index: 485602 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.2534. Min Act: -0.0000

Data Index: 1528564 (Python Code)

Max Activating Token Index: 495

Text #7

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.2894. Min Act: -0.0000

Data Index: 1557941 (Python Code)

Max Activating Token Index: 982

Text #8

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.3053. Min Act: -0.0000

Data Index: 1656557 (Python Code)

Max Activating Token Index: 450

Text #9

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.2658. Min Act: -0.0000

Data Index: 1440432 (Python Code)

Max Activating Token Index: 969

Text #10

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.2487. Min Act: -0.0000

Data Index: 1475249 (Python Code)

Max Activating Token Index: 400

Text #11

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.2766. Min Act: -0.0000

Data Index: 1438365 (Python Code)

Max Activating Token Index: 795

Text #12

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.2155. Min Act: -0.0000

Data Index: 1404206 (Python Code)

Max Activating Token Index: 846

Text #13

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.2339. Min Act: -0.0000

Data Index: 580039 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.2484. Min Act: -0.0000

Data Index: 1416406 (Python Code)

Max Activating Token Index: 683

Text #15

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.2671. Min Act: -0.0000

Data Index: 1525374 (Python Code)

Max Activating Token Index: 895

Text #16

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.2248. Min Act: -0.0000

Data Index: 767192 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.1525. Min Act: -0.0000

Data Index: 1462790 (Python Code)

Max Activating Token Index: 658

Text #18

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.2224. Min Act: -0.0000

Data Index: 1588160 (Python Code)

Max Activating Token Index: 982

Text #19

Max Range: 1.7039. Min Range: -1.7039

Max Act: 1.1723. Min Act: -0.0000

Data Index: 1617130 (Python Code)

Max Activating Token Index: 262