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

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

Neuron 3685 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0745. Min Act: -0.0000

Data Index: 669378 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0536. Min Act: -0.0000

Data Index: 27046 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0529. Min Act: -0.0000

Data Index: 567378 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0485. Min Act: -0.0000

Data Index: 125021 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0512. Min Act: -0.0001

Data Index: 516646 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0520. Min Act: -0.0000

Data Index: 1182912 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0507. Min Act: -0.0000

Data Index: 1066528 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0515. Min Act: -0.0000

Data Index: 932015 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0507. Min Act: -0.0000

Data Index: 929498 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0495. Min Act: -0.0000

Data Index: 1295964 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0483. Min Act: -0.0000

Data Index: 920640 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0482. Min Act: -0.0000

Data Index: 497992 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0484. Min Act: -0.0000

Data Index: 1135768 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0486. Min Act: -0.0000

Data Index: 1235363 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0467. Min Act: -0.0000

Data Index: 1006066 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0526. Min Act: -0.0001

Data Index: 368274 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0490. Min Act: -0.0000

Data Index: 1201476 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0481. Min Act: -0.0000

Data Index: 279472 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0465. Min Act: -0.0000

Data Index: 420963 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0462. Min Act: -0.0000

Data Index: 1050281 (C4 (Web Text))

Max Activating Token Index: 106