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

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

Neuron 1266 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: 0.0703. Min Range: -0.0703

Max Act: 0.0703. Min Act: -0.0003

Data Index: 915375 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0597. Min Act: -0.0003

Data Index: 369633 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0654. Min Act: -0.0003

Data Index: 1266161 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0621. Min Act: -0.0003

Data Index: 1013486 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0664. Min Act: -0.0003

Data Index: 879107 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0494. Min Act: -0.0003

Data Index: 893277 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0622. Min Act: -0.0003

Data Index: 310210 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0600. Min Act: -0.0003

Data Index: 1353663 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0586. Min Act: -0.0003

Data Index: 440897 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0572. Min Act: -0.0003

Data Index: 1172878 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0562. Min Act: -0.0003

Data Index: 449910 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0569. Min Act: -0.0003

Data Index: 1094664 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0580. Min Act: -0.0003

Data Index: 600389 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0650. Min Act: -0.0003

Data Index: 51171 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0604. Min Act: -0.0003

Data Index: 906805 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0563. Min Act: -0.0003

Data Index: 881306 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0573. Min Act: -0.0003

Data Index: 332285 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0589. Min Act: -0.0003

Data Index: 222701 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0568. Min Act: -0.0003

Data Index: 622783 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0630. Min Act: -0.0003

Data Index: 226161 (C4 (Web Text))

Max Activating Token Index: 590