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

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

Neuron 1495 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.8593. Min Act: -0.0002

Data Index: 1522268 (Python Code)

Max Activating Token Index: 217

Text #1

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.7989. Min Act: -0.0002

Data Index: 1410141 (Python Code)

Max Activating Token Index: 232

Text #2

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.8176. Min Act: -0.0002

Data Index: 1590732 (Python Code)

Max Activating Token Index: 236

Text #3

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.7851. Min Act: -0.0002

Data Index: 1555844 (Python Code)

Max Activating Token Index: 280

Text #4

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.8349. Min Act: -0.0002

Data Index: 1519984 (Python Code)

Max Activating Token Index: 788

Text #5

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.7482. Min Act: -0.0002

Data Index: 1646857 (Python Code)

Max Activating Token Index: 340

Text #6

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.6252. Min Act: -0.0002

Data Index: 1386979 (Python Code)

Max Activating Token Index: 192

Text #7

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.5173. Min Act: -0.0002

Data Index: 1571813 (Python Code)

Max Activating Token Index: 936

Text #8

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.5204. Min Act: -0.0002

Data Index: 1445584 (Python Code)

Max Activating Token Index: 961

Text #9

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.5060. Min Act: -0.0002

Data Index: 1398879 (Python Code)

Max Activating Token Index: 392

Text #10

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.4896. Min Act: -0.0002

Data Index: 1611803 (Python Code)

Max Activating Token Index: 1019

Text #11

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.3916. Min Act: -0.0002

Data Index: 1467872 (Python Code)

Max Activating Token Index: 392

Text #12

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.4692. Min Act: -0.0002

Data Index: 1619059 (Python Code)

Max Activating Token Index: 40

Text #13

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.4325. Min Act: -0.0002

Data Index: 1610819 (Python Code)

Max Activating Token Index: 309

Text #14

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.3915. Min Act: -0.0002

Data Index: 1625179 (Python Code)

Max Activating Token Index: 101

Text #15

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.4179. Min Act: -0.0002

Data Index: 1384939 (Python Code)

Max Activating Token Index: 504

Text #16

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.4999. Min Act: -0.0002

Data Index: 1568954 (Python Code)

Max Activating Token Index: 922

Text #17

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.4138. Min Act: -0.0002

Data Index: 1384934 (Python Code)

Max Activating Token Index: 682

Text #18

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.3815. Min Act: -0.0002

Data Index: 1376830 (Python Code)

Max Activating Token Index: 812

Text #19

Max Range: 1.8593. Min Range: -1.8593

Max Act: 1.4156. Min Act: -0.0002

Data Index: 1444701 (Python Code)

Max Activating Token Index: 117