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

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

Neuron 1010 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: 0.0668. Min Range: -0.0668

Max Act: 0.0662. Min Act: -0.0001

Data Index: 443223 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0629. Min Act: -0.0002

Data Index: 739819 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0656. Min Act: -0.0002

Data Index: 324026 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1077637 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1289501 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0628. Min Act: -0.0002

Data Index: 862158 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1211944 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0617. Min Act: -0.0002

Data Index: 680758 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0608. Min Act: -0.0002

Data Index: 835652 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0609. Min Act: -0.0002

Data Index: 501889 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0591. Min Act: -0.0002

Data Index: 568196 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1168424 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1199256 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0606. Min Act: -0.0002

Data Index: 437510 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0576. Min Act: -0.0002

Data Index: 849494 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0629. Min Act: -0.0002

Data Index: 842843 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0597. Min Act: -0.0001

Data Index: 428493 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0596. Min Act: -0.0002

Data Index: 736305 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1288340 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 0.0668. Min Range: -0.0668

Max Act: 0.0576. Min Act: -0.0002

Data Index: 697071 (C4 (Web Text))

Max Activating Token Index: 328