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

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

Neuron 2036 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1566. Min Act: -0.0000

Data Index: 298369 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1394. Min Act: -0.0001

Data Index: 440868 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1394. Min Act: -0.0001

Data Index: 851524 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1217. Min Act: -0.0001

Data Index: 797255 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1284. Min Act: -0.0001

Data Index: 923394 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1237. Min Act: -0.0001

Data Index: 101212 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1210. Min Act: -0.0001

Data Index: 1083895 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1205. Min Act: -0.0001

Data Index: 400592 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1211334 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1085. Min Act: -0.0001

Data Index: 590259 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1157. Min Act: -0.0000

Data Index: 717079 (C4 (Web Text))

Max Activating Token Index: 575

Text #11

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1329161 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1078. Min Act: -0.0001

Data Index: 1246642 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1258546 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1143. Min Act: -0.0001

Data Index: 989121 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1075. Min Act: -0.0001

Data Index: 725969 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1064. Min Act: -0.0001

Data Index: 475705 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1068. Min Act: -0.0001

Data Index: 820740 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1020. Min Act: -0.0001

Data Index: 224570 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.1566. Min Range: -0.1566

Max Act: 0.1038. Min Act: -0.0001

Data Index: 337300 (C4 (Web Text))

Max Activating Token Index: 387