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

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

Neuron 1642 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0746. Min Act: -0.0005

Data Index: 1017751 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0749. Min Act: -0.0005

Data Index: 971519 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0674. Min Act: -0.0005

Data Index: 1279702 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0664. Min Act: -0.0005

Data Index: 318994 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0631. Min Act: -0.0005

Data Index: 77089 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0630. Min Act: -0.0005

Data Index: 1339592 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0641. Min Act: -0.0005

Data Index: 1206658 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0652. Min Act: -0.0005

Data Index: 1075527 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0651. Min Act: -0.0005

Data Index: 8823 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0645. Min Act: -0.0005

Data Index: 775021 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0656. Min Act: -0.0005

Data Index: 422478 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0647. Min Act: -0.0005

Data Index: 617042 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0611. Min Act: -0.0005

Data Index: 367564 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0635. Min Act: -0.0005

Data Index: 142797 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0591. Min Act: -0.0005

Data Index: 1043171 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0611. Min Act: -0.0005

Data Index: 922880 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0621. Min Act: -0.0005

Data Index: 47836 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0621. Min Act: -0.0005

Data Index: 1322548 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0608. Min Act: -0.0005

Data Index: 207739 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0603. Min Act: -0.0005

Data Index: 1319808 (C4 (Web Text))

Max Activating Token Index: 806