Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1339 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0537. Min Act: -0.0004

Data Index: 1136135 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0519. Min Act: -0.0003

Data Index: 180855 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0548. Min Act: -0.0003

Data Index: 471595 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0527. Min Act: -0.0003

Data Index: 204400 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0499. Min Act: -0.0003

Data Index: 1126195 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0523. Min Act: -0.0003

Data Index: 541600 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0532. Min Act: -0.0003

Data Index: 399061 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0509. Min Act: -0.0003

Data Index: 235815 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0499. Min Act: -0.0003

Data Index: 1289624 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0494. Min Act: -0.0003

Data Index: 985279 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1170072 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0512. Min Act: -0.0004

Data Index: 267669 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0506. Min Act: -0.0003

Data Index: 215390 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0512. Min Act: -0.0003

Data Index: 585454 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0512. Min Act: -0.0003

Data Index: 512631 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0537. Min Act: -0.0003

Data Index: 660381 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0508. Min Act: -0.0003

Data Index: 1216670 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0483. Min Act: -0.0003

Data Index: 394269 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0488. Min Act: -0.0003

Data Index: 127941 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0483. Min Act: -0.0003

Data Index: 742966 (C4 (Web Text))

Max Activating Token Index: 334