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

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

Neuron 1015 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0647. Min Act: -0.0002

Data Index: 9100 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1112246 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1083038 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0537. Min Act: -0.0001

Data Index: 894202 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1509784 (Python Code)

Max Activating Token Index: 134

Text #5

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0578. Min Act: -0.0001

Data Index: 1487845 (Python Code)

Max Activating Token Index: 448

Text #6

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1295284 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0614. Min Act: -0.0001

Data Index: 1424243 (Python Code)

Max Activating Token Index: 431

Text #8

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0464. Min Act: -0.0001

Data Index: 567716 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0525. Min Act: -0.0001

Data Index: 420836 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0577. Min Act: -0.0001

Data Index: 411126 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0510. Min Act: -0.0001

Data Index: 446079 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1080482 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0533. Min Act: -0.0001

Data Index: 194803 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0639. Min Act: -0.0001

Data Index: 1057747 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0551. Min Act: -0.0002

Data Index: 360694 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0569. Min Act: -0.0001

Data Index: 85724 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0572. Min Act: -0.0001

Data Index: 1515226 (Python Code)

Max Activating Token Index: 596

Text #18

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1151647 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.0801. Min Range: -0.0801

Max Act: 0.0506. Min Act: -0.0001

Data Index: 379844 (C4 (Web Text))

Max Activating Token Index: 418