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

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

Neuron 1898 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.8434. Min Act: -0.0000

Data Index: 1465740 (Python Code)

Max Activating Token Index: 126

Text #1

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.8424. Min Act: -0.0000

Data Index: 1509343 (Python Code)

Max Activating Token Index: 505

Text #2

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.8161. Min Act: -0.0000

Data Index: 1419097 (Python Code)

Max Activating Token Index: 62

Text #3

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1422981 (Python Code)

Max Activating Token Index: 800

Text #4

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6996. Min Act: -0.0000

Data Index: 1446426 (Python Code)

Max Activating Token Index: 915

Text #5

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1426426 (Python Code)

Max Activating Token Index: 623

Text #6

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.7208. Min Act: -0.0000

Data Index: 1625013 (Python Code)

Max Activating Token Index: 631

Text #7

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1575006 (Python Code)

Max Activating Token Index: 466

Text #8

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6478. Min Act: -0.0000

Data Index: 1606798 (Python Code)

Max Activating Token Index: 289

Text #9

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6891. Min Act: -0.0000

Data Index: 1525765 (Python Code)

Max Activating Token Index: 284

Text #10

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6179. Min Act: -0.0000

Data Index: 1651088 (Python Code)

Max Activating Token Index: 89

Text #11

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1493185 (Python Code)

Max Activating Token Index: 230

Text #12

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1628832 (Python Code)

Max Activating Token Index: 288

Text #13

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1555789 (Python Code)

Max Activating Token Index: 130

Text #14

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1469231 (Python Code)

Max Activating Token Index: 176

Text #15

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.5196. Min Act: -0.0000

Data Index: 1459911 (Python Code)

Max Activating Token Index: 144

Text #16

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1559380 (Python Code)

Max Activating Token Index: 190

Text #17

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1431313 (Python Code)

Max Activating Token Index: 152

Text #18

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.5940. Min Act: -0.0000

Data Index: 1451026 (Python Code)

Max Activating Token Index: 193

Text #19

Max Range: 0.8434. Min Range: -0.8434

Max Act: 0.6098. Min Act: -0.0000

Data Index: 1397965 (Python Code)

Max Activating Token Index: 553