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

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

Neuron 4914 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9100. Min Range: -7.9100

Max Act: 7.9100. Min Act: -0.0000

Data Index: 969993 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 7.9100. Min Range: -7.9100

Max Act: 6.7818. Min Act: -0.0000

Data Index: 75699 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 7.9100. Min Range: -7.9100

Max Act: 6.2303. Min Act: -0.0000

Data Index: 1206156 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 7.9100. Min Range: -7.9100

Max Act: 5.2589. Min Act: -0.0000

Data Index: 670326 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 7.9100. Min Range: -7.9100

Max Act: 6.1224. Min Act: -0.0000

Data Index: 835617 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 7.9100. Min Range: -7.9100

Max Act: 5.9775. Min Act: -0.0000

Data Index: 1169537 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 7.9100. Min Range: -7.9100

Max Act: 5.8453. Min Act: -0.0000

Data Index: 1271201 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 7.9100. Min Range: -7.9100

Max Act: 6.0510. Min Act: -0.0000

Data Index: 855060 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 7.9100. Min Range: -7.9100

Max Act: 5.2583. Min Act: -0.0000

Data Index: 986598 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 7.9100. Min Range: -7.9100

Max Act: 5.3665. Min Act: -0.0000

Data Index: 949641 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 7.9100. Min Range: -7.9100

Max Act: 4.9224. Min Act: -0.0000

Data Index: 1054862 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 7.9100. Min Range: -7.9100

Max Act: 4.9212. Min Act: -0.0000

Data Index: 969444 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 7.9100. Min Range: -7.9100

Max Act: 4.1200. Min Act: -0.0000

Data Index: 663552 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 7.9100. Min Range: -7.9100

Max Act: 3.6524. Min Act: -0.0000

Data Index: 30023 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 7.9100. Min Range: -7.9100

Max Act: 3.2660. Min Act: -0.0000

Data Index: 1183798 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 7.9100. Min Range: -7.9100

Max Act: 2.8923. Min Act: -0.0000

Data Index: 185455 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 7.9100. Min Range: -7.9100

Max Act: 2.6967. Min Act: -0.0000

Data Index: 788603 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 7.9100. Min Range: -7.9100

Max Act: 2.6103. Min Act: -0.0000

Data Index: 1218678 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 7.9100. Min Range: -7.9100

Max Act: 3.1127. Min Act: -0.0000

Data Index: 327718 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 7.9100. Min Range: -7.9100

Max Act: 2.4504. Min Act: -0.0000

Data Index: 396817 (C4 (Web Text))

Max Activating Token Index: 812