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

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

Neuron 2224 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2435. Min Range: -1.2435

Max Act: 1.2224. Min Act: -0.0001

Data Index: 1377856 (Python Code)

Max Activating Token Index: 124

Text #1

Max Range: 1.2435. Min Range: -1.2435

Max Act: 1.1432. Min Act: -0.0001

Data Index: 1364177 (Python Code)

Max Activating Token Index: 915

Text #2

Max Range: 1.2435. Min Range: -1.2435

Max Act: 1.2198. Min Act: -0.0001

Data Index: 1479536 (Python Code)

Max Activating Token Index: 41

Text #3

Max Range: 1.2435. Min Range: -1.2435

Max Act: 1.2435. Min Act: -0.0001

Data Index: 1602090 (Python Code)

Max Activating Token Index: 515

Text #4

Max Range: 1.2435. Min Range: -1.2435

Max Act: 1.1727. Min Act: -0.0001

Data Index: 1560873 (Python Code)

Max Activating Token Index: 160

Text #5

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.9952. Min Act: -0.0001

Data Index: 1482342 (Python Code)

Max Activating Token Index: 53

Text #6

Max Range: 1.2435. Min Range: -1.2435

Max Act: 1.0470. Min Act: -0.0001

Data Index: 1365141 (Python Code)

Max Activating Token Index: 57

Text #7

Max Range: 1.2435. Min Range: -1.2435

Max Act: 1.0573. Min Act: -0.0001

Data Index: 1538401 (Python Code)

Max Activating Token Index: 232

Text #8

Max Range: 1.2435. Min Range: -1.2435

Max Act: 1.0279. Min Act: -0.0001

Data Index: 1643159 (Python Code)

Max Activating Token Index: 722

Text #9

Max Range: 1.2435. Min Range: -1.2435

Max Act: 1.0232. Min Act: -0.0001

Data Index: 1461582 (Python Code)

Max Activating Token Index: 38

Text #10

Max Range: 1.2435. Min Range: -1.2435

Max Act: 1.0034. Min Act: -0.0001

Data Index: 1510859 (Python Code)

Max Activating Token Index: 79

Text #11

Max Range: 1.2435. Min Range: -1.2435

Max Act: 1.0363. Min Act: -0.0001

Data Index: 1482832 (Python Code)

Max Activating Token Index: 128

Text #12

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.9759. Min Act: -0.0001

Data Index: 1631030 (Python Code)

Max Activating Token Index: 227

Text #13

Max Range: 1.2435. Min Range: -1.2435

Max Act: 1.0030. Min Act: -0.0001

Data Index: 1490950 (Python Code)

Max Activating Token Index: 107

Text #14

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.9818. Min Act: -0.0001

Data Index: 1373340 (Python Code)

Max Activating Token Index: 481

Text #15

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.9667. Min Act: -0.0001

Data Index: 1390362 (Python Code)

Max Activating Token Index: 789

Text #16

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.9591. Min Act: -0.0001

Data Index: 1389717 (Python Code)

Max Activating Token Index: 1006

Text #17

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.9868. Min Act: -0.0001

Data Index: 1628080 (Python Code)

Max Activating Token Index: 824

Text #18

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.9132. Min Act: -0.0001

Data Index: 1601820 (Python Code)

Max Activating Token Index: 769

Text #19

Max Range: 1.2435. Min Range: -1.2435

Max Act: 0.9472. Min Act: -0.0001

Data Index: 1559003 (Python Code)

Max Activating Token Index: 124