Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4737 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0712. Min Act: -0.0002

Data Index: 951411 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0661. Min Act: -0.0002

Data Index: 17030 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0585. Min Act: -0.0002

Data Index: 312634 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1201883 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1335864 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0524. Min Act: -0.0002

Data Index: 361677 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0538. Min Act: -0.0002

Data Index: 478878 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0538. Min Act: -0.0002

Data Index: 501450 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1316533 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0525. Min Act: -0.0002

Data Index: 764516 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0519. Min Act: -0.0002

Data Index: 229741 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0516. Min Act: -0.0002

Data Index: 868276 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0515. Min Act: -0.0002

Data Index: 382369 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0510. Min Act: -0.0002

Data Index: 1353350 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1298066 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0514. Min Act: -0.0002

Data Index: 153468 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1197217 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0491. Min Act: -0.0002

Data Index: 210100 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1205765 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1149136 (C4 (Web Text))

Max Activating Token Index: 935