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

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

Neuron 4585 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1059235 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0530. Min Act: -0.0002

Data Index: 305166 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0525. Min Act: -0.0002

Data Index: 541763 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0584. Min Act: -0.0002

Data Index: 458894 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0563. Min Act: -0.0002

Data Index: 918086 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1085532 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0476. Min Act: -0.0002

Data Index: 139102 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1115001 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0562. Min Act: -0.0002

Data Index: 824857 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0633. Min Act: -0.0002

Data Index: 123110 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0451. Min Act: -0.0002

Data Index: 295837 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0492. Min Act: -0.0002

Data Index: 315476 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1066612 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0458. Min Act: -0.0002

Data Index: 759128 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0501. Min Act: -0.0002

Data Index: 893733 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0488. Min Act: -0.0002

Data Index: 804389 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0531. Min Act: -0.0002

Data Index: 714759 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0460. Min Act: -0.0002

Data Index: 317631 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0505. Min Act: -0.0002

Data Index: 79839 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1338250 (C4 (Web Text))

Max Activating Token Index: 6