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

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

Neuron 4610 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.4541. Min Act: -0.0000

Data Index: 1268785 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3843. Min Act: -0.0000

Data Index: 1280557 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3495. Min Act: -0.0000

Data Index: 1310999 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3447. Min Act: -0.0000

Data Index: 993098 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3344. Min Act: -0.0000

Data Index: 1265682 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3355. Min Act: -0.0000

Data Index: 619619 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3327. Min Act: -0.0000

Data Index: 494747 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.3056. Min Act: -0.0000

Data Index: 373570 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2787. Min Act: -0.0000

Data Index: 514928 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2952. Min Act: -0.0000

Data Index: 679648 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2804. Min Act: -0.0000

Data Index: 111490 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2786. Min Act: 0.0000

Data Index: 443967 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2686. Min Act: 0.0000

Data Index: 216127 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2756. Min Act: -0.0000

Data Index: 263694 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2836. Min Act: -0.0000

Data Index: 87525 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1071428 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2633. Min Act: -0.0000

Data Index: 531449 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1114089 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2597. Min Act: -0.0000

Data Index: 1007718 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.4541. Min Range: -0.4541

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1249390 (C4 (Web Text))

Max Activating Token Index: 664