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

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

Neuron 484 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1243. Min Act: -0.0003

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0890. Min Act: -0.0003

Data Index: 916711 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0775. Min Act: -0.0003

Data Index: 341000 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0718. Min Act: -0.0002

Data Index: 993464 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0711. Min Act: -0.0003

Data Index: 831303 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0646. Min Act: -0.0003

Data Index: 1078013 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0683. Min Act: -0.0002

Data Index: 594088 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0641. Min Act: -0.0002

Data Index: 931384 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0638. Min Act: -0.0003

Data Index: 324186 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0638. Min Act: -0.0003

Data Index: 633535 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0630. Min Act: -0.0002

Data Index: 77187 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1177750 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0593. Min Act: -0.0003

Data Index: 760629 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0617. Min Act: -0.0003

Data Index: 878022 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0588. Min Act: -0.0003

Data Index: 1204090 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0566. Min Act: -0.0003

Data Index: 885387 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0574. Min Act: -0.0003

Data Index: 206128 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1114322 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0555. Min Act: -0.0003

Data Index: 6272 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0530. Min Act: -0.0003

Data Index: 190405 (C4 (Web Text))

Max Activating Token Index: 916