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

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

Neuron 1091 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: 0.0741. Min Range: -0.0741

Max Act: 0.0741. Min Act: -0.0003

Data Index: 867187 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0646. Min Act: -0.0003

Data Index: 824357 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0656. Min Act: -0.0004

Data Index: 49170 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0610. Min Act: -0.0003

Data Index: 1207326 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0621. Min Act: -0.0003

Data Index: 1091352 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0571. Min Act: -0.0004

Data Index: 853448 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0514. Min Act: -0.0003

Data Index: 1096883 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0523. Min Act: -0.0003

Data Index: 935878 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0508. Min Act: -0.0003

Data Index: 271998 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0515. Min Act: -0.0003

Data Index: 1296432 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0513. Min Act: -0.0003

Data Index: 803250 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0523. Min Act: -0.0003

Data Index: 256254 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0488. Min Act: -0.0004

Data Index: 1060126 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0505. Min Act: -0.0003

Data Index: 1144394 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0481. Min Act: -0.0003

Data Index: 796824 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0493. Min Act: -0.0003

Data Index: 80107 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0494. Min Act: -0.0003

Data Index: 1204222 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0508. Min Act: -0.0003

Data Index: 1191419 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1261968 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.0741. Min Range: -0.0741

Max Act: 0.0485. Min Act: -0.0003

Data Index: 1119352 (C4 (Web Text))

Max Activating Token Index: 944