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

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

Neuron 833 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1525. Min Act: -0.0003

Data Index: 279015 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1371. Min Act: -0.0003

Data Index: 509478 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1252. Min Act: -0.0003

Data Index: 689095 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1257. Min Act: -0.0003

Data Index: 184701 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1187. Min Act: -0.0003

Data Index: 786819 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1206. Min Act: -0.0003

Data Index: 1220773 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1223. Min Act: -0.0003

Data Index: 849928 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1133. Min Act: -0.0003

Data Index: 394656 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1169. Min Act: -0.0003

Data Index: 1094390 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1154. Min Act: -0.0003

Data Index: 1241670 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1204. Min Act: -0.0003

Data Index: 576400 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1047. Min Act: -0.0003

Data Index: 386228 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1175. Min Act: -0.0003

Data Index: 653152 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.0867. Min Act: -0.0003

Data Index: 204500 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1114. Min Act: -0.0003

Data Index: 773127 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1127. Min Act: -0.0003

Data Index: 433175 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1022. Min Act: -0.0003

Data Index: 311067 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1067. Min Act: -0.0003

Data Index: 1239087 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1039. Min Act: -0.0003

Data Index: 846268 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1201. Min Act: -0.0003

Data Index: 310483 (C4 (Web Text))

Max Activating Token Index: 752