Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 576 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.8030. Min Act: -0.0000

Data Index: 415448 (C4 (Web Text))

Max Activating Token Index: 358

Text #1

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.7830. Min Act: -0.0000

Data Index: 154987 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.6349. Min Act: -0.0000

Data Index: 918916 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.5123. Min Act: -0.0000

Data Index: 209549 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.5608. Min Act: -0.0000

Data Index: 467520 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.5463. Min Act: -0.0000

Data Index: 540551 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1001779 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.5183. Min Act: -0.0000

Data Index: 428571 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1221877 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.5064. Min Act: -0.0000

Data Index: 659606 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.4966. Min Act: -0.0000

Data Index: 511945 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.4960. Min Act: -0.0000

Data Index: 29599 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.4946. Min Act: -0.0000

Data Index: 769061 (C4 (Web Text))

Max Activating Token Index: 851

Text #13

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.5122. Min Act: -0.0000

Data Index: 811432 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.4757. Min Act: -0.0000

Data Index: 372025 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.4708. Min Act: -0.0000

Data Index: 743253 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.4545. Min Act: -0.0000

Data Index: 824444 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.4635. Min Act: -0.0000

Data Index: 306749 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.4788. Min Act: -0.0000

Data Index: 271525 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.8030. Min Range: -0.8030

Max Act: 0.4654. Min Act: -0.0000

Data Index: 638996 (C4 (Web Text))

Max Activating Token Index: 81