Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1273 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.5531. Min Act: -0.0004

Data Index: 737153 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.6684. Min Act: -0.0004

Data Index: 139630 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.4870. Min Act: -0.0004

Data Index: 653960 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.5622. Min Act: -0.0004

Data Index: 938043 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.7592. Min Act: -0.0004

Data Index: 1071775 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.5208. Min Act: -0.0004

Data Index: 271632 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.6772. Min Act: -0.0004

Data Index: 246170 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.4041. Min Act: -0.0004

Data Index: 524189 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.4809. Min Act: -0.0004

Data Index: 1056052 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.3578. Min Act: -0.0004

Data Index: 25159 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.5306. Min Act: -0.0004

Data Index: 470006 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.4759. Min Act: -0.0004

Data Index: 55980 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.3609. Min Act: -0.0004

Data Index: 123563 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.5548. Min Act: -0.0004

Data Index: 29320 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.5152. Min Act: -0.0004

Data Index: 198438 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.4496. Min Act: -0.0004

Data Index: 503708 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.4677. Min Act: -0.0004

Data Index: 734827 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.4930. Min Act: -0.0004

Data Index: 345710 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.6144. Min Act: -0.0004

Data Index: 720143 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.7592. Min Range: -0.7592

Max Act: 0.5588. Min Act: -0.0004

Data Index: 1184055 (C4 (Web Text))

Max Activating Token Index: 713