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

Dataset: The Pile

Neuron 3654 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0835. Min Range: -5.0835

Max Act: 5.0835. Min Act: -0.0000

Data Index: 256507 (The Pile)

Max Activating Token Index: 251

Text #1

Max Range: 5.0835. Min Range: -5.0835

Max Act: 3.6940. Min Act: -0.0000

Data Index: 1238926 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 5.0835. Min Range: -5.0835

Max Act: 3.1801. Min Act: -0.0000

Data Index: 1208633 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 5.0835. Min Range: -5.0835

Max Act: 3.1733. Min Act: -0.0000

Data Index: 197135 (The Pile)

Max Activating Token Index: 121

Text #4

Max Range: 5.0835. Min Range: -5.0835

Max Act: 2.5890. Min Act: -0.0000

Data Index: 1693629 (The Pile)

Max Activating Token Index: 921

Text #5

Max Range: 5.0835. Min Range: -5.0835

Max Act: 2.5419. Min Act: -0.0000

Data Index: 317245 (The Pile)

Max Activating Token Index: 896

Text #6

Max Range: 5.0835. Min Range: -5.0835

Max Act: 2.7984. Min Act: -0.0000

Data Index: 502479 (The Pile)

Max Activating Token Index: 474

Text #7

Max Range: 5.0835. Min Range: -5.0835

Max Act: 2.5228. Min Act: -0.0000

Data Index: 17652 (The Pile)

Max Activating Token Index: 750

Text #8

Max Range: 5.0835. Min Range: -5.0835

Max Act: 2.4988. Min Act: -0.0000

Data Index: 883153 (The Pile)

Max Activating Token Index: 955

Text #9

Max Range: 5.0835. Min Range: -5.0835

Max Act: 2.4426. Min Act: -0.0000

Data Index: 69685 (The Pile)

Max Activating Token Index: 952

Text #10

Max Range: 5.0835. Min Range: -5.0835

Max Act: 2.2766. Min Act: -0.0000

Data Index: 16730 (The Pile)

Max Activating Token Index: 535

Text #11

Max Range: 5.0835. Min Range: -5.0835

Max Act: 2.2583. Min Act: -0.0000

Data Index: 1493552 (The Pile)

Max Activating Token Index: 1000

Text #12

Max Range: 5.0835. Min Range: -5.0835

Max Act: 2.3340. Min Act: -0.0000

Data Index: 1200466 (The Pile)

Max Activating Token Index: 902

Text #13

Max Range: 5.0835. Min Range: -5.0835

Max Act: 2.4462. Min Act: -0.0000

Data Index: 720980 (The Pile)

Max Activating Token Index: 819

Text #14

Max Range: 5.0835. Min Range: -5.0835

Max Act: 2.2597. Min Act: -0.0000

Data Index: 1728681 (The Pile)

Max Activating Token Index: 486

Text #15

Max Range: 5.0835. Min Range: -5.0835

Max Act: 1.8605. Min Act: -0.0000

Data Index: 592712 (The Pile)

Max Activating Token Index: 610

Text #16

Max Range: 5.0835. Min Range: -5.0835

Max Act: 2.1008. Min Act: -0.0000

Data Index: 1284749 (The Pile)

Max Activating Token Index: 751

Text #17

Max Range: 5.0835. Min Range: -5.0835

Max Act: 2.2899. Min Act: -0.0000

Data Index: 936815 (The Pile)

Max Activating Token Index: 686

Text #18

Max Range: 5.0835. Min Range: -5.0835

Max Act: 2.3755. Min Act: -0.0000

Data Index: 618719 (The Pile)

Max Activating Token Index: 929

Text #19

Max Range: 5.0835. Min Range: -5.0835

Max Act: 2.0545. Min Act: -0.0000

Data Index: 1057318 (The Pile)

Max Activating Token Index: 479