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

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

Neuron 1849 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: 0.3372. Min Range: -0.3372

Max Act: 0.3269. Min Act: -0.0001

Data Index: 1100262 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.3372. Min Act: -0.0001

Data Index: 920070 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2630. Min Act: -0.0001

Data Index: 360865 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2477. Min Act: -0.0000

Data Index: 1545036 (Python Code)

Max Activating Token Index: 260

Text #4

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1397944 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2176. Min Act: -0.0001

Data Index: 1078865 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2456. Min Act: -0.0000

Data Index: 1572513 (Python Code)

Max Activating Token Index: 1009

Text #7

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1524072 (Python Code)

Max Activating Token Index: 802

Text #8

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1368692 (Python Code)

Max Activating Token Index: 811

Text #9

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2302. Min Act: -0.0001

Data Index: 1526731 (Python Code)

Max Activating Token Index: 627

Text #10

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2117. Min Act: -0.0001

Data Index: 418182 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1451675 (Python Code)

Max Activating Token Index: 855

Text #12

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1608617 (Python Code)

Max Activating Token Index: 840

Text #13

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1599759 (Python Code)

Max Activating Token Index: 698

Text #14

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2220. Min Act: -0.0000

Data Index: 1645525 (Python Code)

Max Activating Token Index: 616

Text #15

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2114. Min Act: -0.0000

Data Index: 1528721 (Python Code)

Max Activating Token Index: 842

Text #16

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2095. Min Act: -0.0001

Data Index: 165754 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1634633 (Python Code)

Max Activating Token Index: 898

Text #18

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1594300 (Python Code)

Max Activating Token Index: 1020

Text #19

Max Range: 0.3372. Min Range: -0.3372

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1534658 (Python Code)

Max Activating Token Index: 762