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

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

Neuron 2559 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: 0.9461. Min Range: -0.9461

Max Act: 0.9461. Min Act: -0.0001

Data Index: 1269853 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.8340. Min Act: -0.0001

Data Index: 867291 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7866. Min Act: -0.0001

Data Index: 1298082 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.8129. Min Act: -0.0001

Data Index: 373005 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.8052. Min Act: -0.0001

Data Index: 102123 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7462. Min Act: -0.0001

Data Index: 851159 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7441. Min Act: -0.0001

Data Index: 663075 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.6710. Min Act: -0.0001

Data Index: 1342056 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7529. Min Act: -0.0001

Data Index: 1323034 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7862. Min Act: -0.0001

Data Index: 163711 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7441. Min Act: -0.0000

Data Index: 961321 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.6990. Min Act: -0.0001

Data Index: 911658 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7456. Min Act: -0.0001

Data Index: 873409 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7082. Min Act: -0.0001

Data Index: 884141 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7278. Min Act: -0.0001

Data Index: 675479 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.6850. Min Act: -0.0001

Data Index: 676134 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7143. Min Act: -0.0001

Data Index: 1045964 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.6720. Min Act: -0.0001

Data Index: 945393 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.7391. Min Act: -0.0001

Data Index: 806303 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.9461. Min Range: -0.9461

Max Act: 0.6939. Min Act: -0.0001

Data Index: 1027418 (C4 (Web Text))

Max Activating Token Index: 775