Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 16 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2293. Min Act: -0.0001

Data Index: 851326 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2170. Min Act: -0.0001

Data Index: 923206 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2210. Min Act: -0.0001

Data Index: 122850 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2195. Min Act: -0.0001

Data Index: 1260809 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2164. Min Act: -0.0000

Data Index: 349216 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2150. Min Act: -0.0000

Data Index: 111897 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2116. Min Act: -0.0001

Data Index: 1002831 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1996. Min Act: -0.0000

Data Index: 1180909 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.2058. Min Act: -0.0000

Data Index: 569505 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1922. Min Act: -0.0001

Data Index: 1242124 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1969. Min Act: -0.0001

Data Index: 1155692 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1068385 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1857. Min Act: -0.0001

Data Index: 878671 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1765. Min Act: -0.0000

Data Index: 979015 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1953. Min Act: -0.0000

Data Index: 657440 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1929. Min Act: -0.0000

Data Index: 317741 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1791. Min Act: -0.0001

Data Index: 909122 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1788. Min Act: -0.0001

Data Index: 274362 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1835. Min Act: -0.0000

Data Index: 555799 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.2293. Min Range: -0.2293

Max Act: 0.1821. Min Act: -0.0001

Data Index: 1195218 (C4 (Web Text))

Max Activating Token Index: 751