Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4964 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1419. Min Act: -0.0003

Data Index: 984785 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1331. Min Act: -0.0003

Data Index: 1218751 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1316. Min Act: -0.0003

Data Index: 912149 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1259. Min Act: -0.0003

Data Index: 1343941 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1250. Min Act: -0.0003

Data Index: 1284020 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1261. Min Act: -0.0003

Data Index: 662645 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1336. Min Act: -0.0003

Data Index: 1261415 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1281. Min Act: -0.0002

Data Index: 779123 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1149. Min Act: -0.0003

Data Index: 852876 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1275. Min Act: -0.0003

Data Index: 508317 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1224. Min Act: -0.0003

Data Index: 24980 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1167. Min Act: -0.0003

Data Index: 872034 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1112. Min Act: -0.0003

Data Index: 260235 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1181. Min Act: -0.0003

Data Index: 601448 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1093. Min Act: -0.0003

Data Index: 530087 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1162. Min Act: -0.0003

Data Index: 199093 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1109. Min Act: -0.0003

Data Index: 529583 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1101. Min Act: -0.0003

Data Index: 542338 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.0978. Min Act: -0.0003

Data Index: 895915 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1055. Min Act: -0.0003

Data Index: 278033 (C4 (Web Text))

Max Activating Token Index: 525