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

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

Neuron 572 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.5043. Min Act: -0.0001

Data Index: 345362 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.4693. Min Act: -0.0001

Data Index: 512146 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.3472. Min Act: -0.0000

Data Index: 819463 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.3450. Min Act: -0.0000

Data Index: 281125 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.3558. Min Act: -0.0000

Data Index: 99291 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.3530. Min Act: -0.0000

Data Index: 622473 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.3411. Min Act: -0.0001

Data Index: 519949 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.3350. Min Act: -0.0000

Data Index: 896634 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.3473. Min Act: -0.0001

Data Index: 1156986 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.2705. Min Act: -0.0001

Data Index: 952689 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.2866. Min Act: -0.0000

Data Index: 666553 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.2946. Min Act: -0.0000

Data Index: 1072388 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.2940. Min Act: -0.0001

Data Index: 370615 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.2592. Min Act: -0.0000

Data Index: 993919 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.2828. Min Act: -0.0000

Data Index: 1321245 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.3017. Min Act: -0.0000

Data Index: 700624 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.2860. Min Act: -0.0001

Data Index: 1079126 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.2733. Min Act: -0.0001

Data Index: 1254150 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.2348. Min Act: -0.0001

Data Index: 755905 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 0.5043. Min Range: -0.5043

Max Act: 0.2427. Min Act: -0.0001

Data Index: 194886 (C4 (Web Text))

Max Activating Token Index: 112