Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2021 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0675. Min Act: -0.0003

Data Index: 301245 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0607. Min Act: -0.0003

Data Index: 772002 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0617. Min Act: -0.0003

Data Index: 975973 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0606. Min Act: -0.0003

Data Index: 701872 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0556. Min Act: -0.0003

Data Index: 459211 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0536. Min Act: -0.0003

Data Index: 1190772 (C4 (Web Text))

Max Activating Token Index: 431

Text #6

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0508. Min Act: -0.0003

Data Index: 263908 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0535. Min Act: -0.0003

Data Index: 798845 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0508. Min Act: -0.0003

Data Index: 718115 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1155043 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0496. Min Act: -0.0003

Data Index: 553627 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0489. Min Act: -0.0004

Data Index: 25149 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0499. Min Act: -0.0003

Data Index: 41260 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0457. Min Act: -0.0003

Data Index: 563442 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0445. Min Act: -0.0003

Data Index: 187425 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0470. Min Act: -0.0003

Data Index: 100371 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0484. Min Act: -0.0003

Data Index: 464137 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0467. Min Act: -0.0003

Data Index: 283922 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1192465 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 0.0675. Min Range: -0.0675

Max Act: 0.0446. Min Act: -0.0003

Data Index: 414692 (C4 (Web Text))

Max Activating Token Index: 985