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

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

Neuron 3671 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: 0.0974. Min Range: -0.0974

Max Act: 0.0974. Min Act: -0.0002

Data Index: 263105 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0770. Min Act: -0.0002

Data Index: 977266 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1037275 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1277574 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0714. Min Act: -0.0002

Data Index: 521935 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1249982 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0695. Min Act: -0.0002

Data Index: 553143 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0668. Min Act: -0.0002

Data Index: 834177 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0654. Min Act: -0.0002

Data Index: 161808 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0652. Min Act: -0.0002

Data Index: 801931 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0630. Min Act: -0.0002

Data Index: 748459 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1262944 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0631. Min Act: -0.0002

Data Index: 646229 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1255677 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0647. Min Act: -0.0002

Data Index: 547088 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0597. Min Act: -0.0002

Data Index: 791488 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0571. Min Act: -0.0002

Data Index: 557038 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1219472 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1237367 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0616. Min Act: -0.0002

Data Index: 539466 (C4 (Web Text))

Max Activating Token Index: 400