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

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

Neuron 1152 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2981. Min Act: -0.0001

Data Index: 775136 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2831. Min Act: -0.0001

Data Index: 157391 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2753. Min Act: -0.0001

Data Index: 301349 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2775. Min Act: -0.0001

Data Index: 855125 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2873. Min Act: -0.0001

Data Index: 1164582 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2845. Min Act: -0.0001

Data Index: 843523 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2891. Min Act: -0.0001

Data Index: 476078 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2792. Min Act: -0.0001

Data Index: 776520 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2785. Min Act: -0.0001

Data Index: 790611 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2790. Min Act: -0.0001

Data Index: 429320 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2725. Min Act: -0.0001

Data Index: 1309137 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2640. Min Act: -0.0001

Data Index: 572613 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2733. Min Act: -0.0001

Data Index: 341050 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2731. Min Act: -0.0001

Data Index: 1127712 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2718. Min Act: -0.0001

Data Index: 1211797 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2616. Min Act: -0.0001

Data Index: 844507 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2702. Min Act: -0.0001

Data Index: 433470 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2707. Min Act: -0.0001

Data Index: 1010038 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2683. Min Act: -0.0001

Data Index: 310492 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.2981. Min Range: -0.2981

Max Act: 0.2690. Min Act: -0.0001

Data Index: 460663 (C4 (Web Text))

Max Activating Token Index: 378