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

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

Neuron 3975 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: 0.3417. Min Range: -0.3417

Max Act: 0.3275. Min Act: -0.0000

Data Index: 1582622 (Python Code)

Max Activating Token Index: 225

Text #1

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3338. Min Act: -0.0000

Data Index: 1532545 (Python Code)

Max Activating Token Index: 100

Text #2

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1443350 (Python Code)

Max Activating Token Index: 858

Text #3

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1443176 (Python Code)

Max Activating Token Index: 235

Text #4

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1433742 (Python Code)

Max Activating Token Index: 254

Text #5

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3324. Min Act: -0.0000

Data Index: 1490246 (Python Code)

Max Activating Token Index: 182

Text #6

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1632957 (Python Code)

Max Activating Token Index: 836

Text #7

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3305. Min Act: -0.0000

Data Index: 1625473 (Python Code)

Max Activating Token Index: 194

Text #8

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3165. Min Act: -0.0000

Data Index: 1402514 (Python Code)

Max Activating Token Index: 187

Text #9

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3167. Min Act: -0.0000

Data Index: 1556272 (Python Code)

Max Activating Token Index: 176

Text #10

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3347. Min Act: -0.0000

Data Index: 1438468 (Python Code)

Max Activating Token Index: 328

Text #11

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3056. Min Act: -0.0000

Data Index: 1513842 (Python Code)

Max Activating Token Index: 815

Text #12

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.2947. Min Act: -0.0000

Data Index: 1581105 (Python Code)

Max Activating Token Index: 157

Text #13

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3213. Min Act: -0.0001

Data Index: 1484995 (Python Code)

Max Activating Token Index: 212

Text #14

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1494315 (Python Code)

Max Activating Token Index: 888

Text #15

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3157. Min Act: -0.0000

Data Index: 1389387 (Python Code)

Max Activating Token Index: 946

Text #16

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3100. Min Act: -0.0000

Data Index: 1412436 (Python Code)

Max Activating Token Index: 123

Text #17

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3169. Min Act: -0.0000

Data Index: 1399217 (Python Code)

Max Activating Token Index: 977

Text #18

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1553041 (Python Code)

Max Activating Token Index: 110

Text #19

Max Range: 0.3417. Min Range: -0.3417

Max Act: 0.3188. Min Act: -0.0001

Data Index: 1440099 (Python Code)

Max Activating Token Index: 158