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

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

Neuron 3445 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6552. Min Range: -1.6552

Max Act: 1.6552. Min Act: -0.0002

Data Index: 1122608 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 1.6552. Min Range: -1.6552

Max Act: 1.3419. Min Act: -0.0002

Data Index: 347683 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 1.6552. Min Range: -1.6552

Max Act: 1.1286. Min Act: -0.0001

Data Index: 897708 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 1.6552. Min Range: -1.6552

Max Act: 1.1190. Min Act: -0.0002

Data Index: 1327196 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 1.6552. Min Range: -1.6552

Max Act: 1.0662. Min Act: -0.0001

Data Index: 700446 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 1.6552. Min Range: -1.6552

Max Act: 1.0493. Min Act: -0.0002

Data Index: 319947 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 1.6552. Min Range: -1.6552

Max Act: 1.0839. Min Act: -0.0002

Data Index: 673633 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 1.6552. Min Range: -1.6552

Max Act: 0.9882. Min Act: -0.0002

Data Index: 712218 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 1.6552. Min Range: -1.6552

Max Act: 1.0017. Min Act: -0.0002

Data Index: 212942 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 1.6552. Min Range: -1.6552

Max Act: 0.9934. Min Act: -0.0002

Data Index: 429997 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 1.6552. Min Range: -1.6552

Max Act: 0.8948. Min Act: -0.0002

Data Index: 860089 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 1.6552. Min Range: -1.6552

Max Act: 0.9463. Min Act: -0.0001

Data Index: 1223865 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 1.6552. Min Range: -1.6552

Max Act: 0.9060. Min Act: -0.0002

Data Index: 301254 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 1.6552. Min Range: -1.6552

Max Act: 0.8497. Min Act: -0.0002

Data Index: 607657 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 1.6552. Min Range: -1.6552

Max Act: 0.9570. Min Act: -0.0002

Data Index: 456187 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 1.6552. Min Range: -1.6552

Max Act: 0.8905. Min Act: -0.0001

Data Index: 781068 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 1.6552. Min Range: -1.6552

Max Act: 0.8877. Min Act: -0.0002

Data Index: 637758 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 1.6552. Min Range: -1.6552

Max Act: 1.0654. Min Act: -0.0002

Data Index: 568813 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 1.6552. Min Range: -1.6552

Max Act: 0.8706. Min Act: -0.0002

Data Index: 968654 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 1.6552. Min Range: -1.6552

Max Act: 0.8428. Min Act: -0.0001

Data Index: 1180191 (C4 (Web Text))

Max Activating Token Index: 257