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

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

Neuron 1987 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1405. Min Act: -0.0001

Data Index: 97255 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1268. Min Act: -0.0001

Data Index: 1110679 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1169. Min Act: -0.0001

Data Index: 778734 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1246. Min Act: -0.0001

Data Index: 208668 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1159. Min Act: -0.0001

Data Index: 526114 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1159. Min Act: -0.0001

Data Index: 319081 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1149. Min Act: -0.0001

Data Index: 515455 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1278. Min Act: -0.0001

Data Index: 605001 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1128. Min Act: -0.0001

Data Index: 319307 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1175. Min Act: -0.0001

Data Index: 515290 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1252. Min Act: -0.0001

Data Index: 267272 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1046. Min Act: -0.0001

Data Index: 172905 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1150. Min Act: -0.0001

Data Index: 686236 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1229. Min Act: -0.0001

Data Index: 101784 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1093. Min Act: -0.0001

Data Index: 433716 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1037. Min Act: -0.0001

Data Index: 1203846 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1079. Min Act: -0.0001

Data Index: 652625 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1130. Min Act: -0.0001

Data Index: 1176511 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1125. Min Act: -0.0001

Data Index: 139174 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.1405. Min Range: -0.1405

Max Act: 0.1051. Min Act: -0.0001

Data Index: 1168681 (C4 (Web Text))

Max Activating Token Index: 68