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

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

Neuron 2886 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1300. Min Act: -0.0001

Data Index: 256959 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1260. Min Act: -0.0001

Data Index: 251133 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1176. Min Act: -0.0001

Data Index: 1193383 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1320271 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1193. Min Act: -0.0002

Data Index: 365629 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1158. Min Act: -0.0002

Data Index: 428107 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1153. Min Act: -0.0002

Data Index: 62200 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1188. Min Act: -0.0001

Data Index: 138926 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1111. Min Act: -0.0002

Data Index: 1344987 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1204190 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1133. Min Act: -0.0001

Data Index: 414241 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1128. Min Act: -0.0002

Data Index: 122453 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1089. Min Act: -0.0002

Data Index: 185173 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1153. Min Act: -0.0001

Data Index: 1209054 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1108. Min Act: -0.0002

Data Index: 415904 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1057. Min Act: -0.0001

Data Index: 630111 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1061. Min Act: -0.0001

Data Index: 520810 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1085. Min Act: -0.0001

Data Index: 207439 (C4 (Web Text))

Max Activating Token Index: 744

Text #18

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1075. Min Act: -0.0001

Data Index: 876292 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 0.1300. Min Range: -0.1300

Max Act: 0.1039. Min Act: -0.0001

Data Index: 774905 (C4 (Web Text))

Max Activating Token Index: 765