Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1821 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1295200 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0600. Min Act: -0.0003

Data Index: 31061 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0605. Min Act: 0.0000

Data Index: 805197 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1265062 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0549. Min Act: -0.0002

Data Index: 470770 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0566. Min Act: -0.0003

Data Index: 848451 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0542. Min Act: -0.0003

Data Index: 1175746 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0552. Min Act: -0.0002

Data Index: 40544 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0551. Min Act: 0.0001

Data Index: 814223 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0563. Min Act: -0.0003

Data Index: 26555 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0551. Min Act: -0.0001

Data Index: 182782 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0554. Min Act: 0.0001

Data Index: 581624 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0558. Min Act: -0.0001

Data Index: 327703 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0545. Min Act: -0.0002

Data Index: 915053 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0539. Min Act: -0.0003

Data Index: 645841 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0537. Min Act: -0.0003

Data Index: 502979 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0528. Min Act: -0.0002

Data Index: 484051 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0547. Min Act: -0.0003

Data Index: 340965 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0510. Min Act: -0.0002

Data Index: 398169 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0518. Min Act: -0.0003

Data Index: 236884 (C4 (Web Text))

Max Activating Token Index: 599