Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2088 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1576. Min Act: -0.0001

Data Index: 531602 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1576. Min Act: -0.0001

Data Index: 599459 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1414. Min Act: -0.0001

Data Index: 567166 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1384. Min Act: -0.0001

Data Index: 606018 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1401. Min Act: -0.0001

Data Index: 843413 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1373. Min Act: -0.0001

Data Index: 26881 (C4 (Web Text))

Max Activating Token Index: 845

Text #6

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1265. Min Act: -0.0001

Data Index: 230988 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1223. Min Act: -0.0001

Data Index: 555107 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1199. Min Act: -0.0001

Data Index: 1098991 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1159. Min Act: -0.0001

Data Index: 619427 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1141. Min Act: -0.0001

Data Index: 706152 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1170. Min Act: -0.0001

Data Index: 656977 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1131. Min Act: -0.0001

Data Index: 29566 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1169. Min Act: -0.0001

Data Index: 359797 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1168. Min Act: -0.0001

Data Index: 1012183 (C4 (Web Text))

Max Activating Token Index: 173

Text #15

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1212. Min Act: -0.0001

Data Index: 155683 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1161. Min Act: -0.0001

Data Index: 910847 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1138. Min Act: -0.0001

Data Index: 888994 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1083. Min Act: -0.0001

Data Index: 316216 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 0.1576. Min Range: -0.1576

Max Act: 0.1160. Min Act: -0.0001

Data Index: 553929 (C4 (Web Text))

Max Activating Token Index: 913