Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1275 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1023501 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0602. Min Act: -0.0001

Data Index: 556395 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0627. Min Act: -0.0002

Data Index: 183147 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1339015 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0565. Min Act: -0.0001

Data Index: 1004484 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0545. Min Act: -0.0002

Data Index: 920474 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0554. Min Act: -0.0001

Data Index: 645270 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0541. Min Act: -0.0002

Data Index: 111912 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0512. Min Act: -0.0002

Data Index: 273094 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0493. Min Act: -0.0001

Data Index: 666102 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0505. Min Act: -0.0002

Data Index: 91126 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0498. Min Act: -0.0002

Data Index: 667888 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0499. Min Act: -0.0001

Data Index: 814325 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0476. Min Act: -0.0002

Data Index: 808716 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0460. Min Act: -0.0002

Data Index: 781446 (C4 (Web Text))

Max Activating Token Index: 281

Text #15

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0478. Min Act: -0.0002

Data Index: 4919 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0471. Min Act: -0.0002

Data Index: 395898 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0459. Min Act: -0.0001

Data Index: 495272 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0465. Min Act: -0.0002

Data Index: 35844 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0456. Min Act: -0.0002

Data Index: 237793 (C4 (Web Text))

Max Activating Token Index: 87