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

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

Neuron 1281 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: 0.1623. Min Range: -0.1623

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1010894 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1460. Min Act: -0.0001

Data Index: 1500508 (Python Code)

Max Activating Token Index: 176

Text #2

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1421. Min Act: -0.0001

Data Index: 510029 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1363. Min Act: -0.0001

Data Index: 403966 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1349. Min Act: -0.0001

Data Index: 1173161 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1336. Min Act: -0.0000

Data Index: 901901 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1245. Min Act: -0.0001

Data Index: 573864 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1171. Min Act: 0.0000

Data Index: 1096167 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1130. Min Act: -0.0001

Data Index: 1221230 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1167. Min Act: -0.0001

Data Index: 1224710 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1169. Min Act: -0.0001

Data Index: 1255207 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1085. Min Act: -0.0000

Data Index: 179955 (C4 (Web Text))

Max Activating Token Index: 363

Text #12

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1163. Min Act: -0.0001

Data Index: 149264 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1145. Min Act: -0.0001

Data Index: 157168 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1143. Min Act: -0.0001

Data Index: 775321 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1136. Min Act: -0.0000

Data Index: 524122 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1093. Min Act: -0.0001

Data Index: 915282 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1086. Min Act: -0.0001

Data Index: 1033952 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1122. Min Act: -0.0001

Data Index: 554686 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1040. Min Act: -0.0001

Data Index: 558639 (C4 (Web Text))

Max Activating Token Index: 739