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

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

Neuron 634 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1505. Min Act: -0.0000

Data Index: 983724 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1316. Min Act: -0.0000

Data Index: 542340 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1003353 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1205808 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1323. Min Act: -0.0000

Data Index: 772719 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1308. Min Act: -0.0000

Data Index: 453811 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1297. Min Act: -0.0000

Data Index: 24751 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1338. Min Act: -0.0000

Data Index: 511607 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1525. Min Act: -0.0000

Data Index: 660002 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1217. Min Act: -0.0000

Data Index: 427519 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1273. Min Act: -0.0000

Data Index: 170932 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1348. Min Act: -0.0000

Data Index: 850612 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1194. Min Act: -0.0000

Data Index: 252693 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1159. Min Act: -0.0000

Data Index: 1214408 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1145. Min Act: -0.0000

Data Index: 1268924 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1063. Min Act: -0.0000

Data Index: 894811 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1171. Min Act: -0.0000

Data Index: 436995 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1342010 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1102. Min Act: -0.0000

Data Index: 467912 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1089. Min Act: -0.0000

Data Index: 194718 (C4 (Web Text))

Max Activating Token Index: 962