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

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

Neuron 812 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.8892. Min Act: -0.0000

Data Index: 659812 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.6695. Min Act: -0.0000

Data Index: 1124126 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.5944. Min Act: -0.0000

Data Index: 1261353 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.5137. Min Act: -0.0000

Data Index: 1255714 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.4935. Min Act: -0.0000

Data Index: 1309925 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.4766. Min Act: -0.0000

Data Index: 913598 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.4937. Min Act: -0.0000

Data Index: 367515 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.4791. Min Act: -0.0000

Data Index: 1264307 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.4250. Min Act: -0.0000

Data Index: 1083473 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.4231. Min Act: -0.0000

Data Index: 1469287 (Python Code)

Max Activating Token Index: 295

Text #10

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.3735. Min Act: -0.0000

Data Index: 391555 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.3208. Min Act: -0.0000

Data Index: 57054 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.3595. Min Act: -0.0000

Data Index: 1613479 (Python Code)

Max Activating Token Index: 515

Text #13

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.4247. Min Act: -0.0000

Data Index: 1219519 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.4592. Min Act: -0.0000

Data Index: 428294 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.3450. Min Act: -0.0000

Data Index: 837014 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.3067. Min Act: -0.0000

Data Index: 1233745 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.3096. Min Act: -0.0000

Data Index: 414718 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.2631. Min Act: -0.0000

Data Index: 1561386 (Python Code)

Max Activating Token Index: 263

Text #19

Max Range: 1.8892. Min Range: -1.8892

Max Act: 1.3018. Min Act: -0.0000

Data Index: 673864 (C4 (Web Text))

Max Activating Token Index: 467