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

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

Neuron 2268 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2459. Min Act: -0.0001

Data Index: 303762 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2129. Min Act: -0.0001

Data Index: 375592 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2249. Min Act: -0.0000

Data Index: 475989 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2325. Min Act: -0.0001

Data Index: 345515 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2289. Min Act: -0.0000

Data Index: 1415249 (Python Code)

Max Activating Token Index: 483

Text #5

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2172. Min Act: -0.0001

Data Index: 685588 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2249. Min Act: -0.0000

Data Index: 1269860 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2150. Min Act: -0.0000

Data Index: 470764 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2298. Min Act: -0.0001

Data Index: 1296471 (C4 (Web Text))

Max Activating Token Index: 508

Text #9

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2251. Min Act: -0.0001

Data Index: 1010663 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2178. Min Act: -0.0001

Data Index: 1336349 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2253. Min Act: -0.0001

Data Index: 1295391 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2169. Min Act: -0.0001

Data Index: 1482178 (Python Code)

Max Activating Token Index: 1009

Text #13

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2145. Min Act: -0.0001

Data Index: 1056034 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2072. Min Act: -0.0001

Data Index: 197520 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2132. Min Act: -0.0001

Data Index: 1450754 (Python Code)

Max Activating Token Index: 161

Text #16

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2131. Min Act: -0.0001

Data Index: 12331 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2118. Min Act: -0.0001

Data Index: 1225865 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2252. Min Act: -0.0001

Data Index: 194541 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.2459. Min Range: -0.2459

Max Act: 0.2110. Min Act: -0.0000

Data Index: 1048892 (C4 (Web Text))

Max Activating Token Index: 527