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

Dataset: The Pile

Neuron 2630 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.4774. Min Act: -0.0000

Data Index: 1719599 (The Pile)

Max Activating Token Index: 339

Text #1

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.2633. Min Act: -0.0000

Data Index: 1357897 (The Pile)

Max Activating Token Index: 746

Text #2

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.1404. Min Act: -0.0000

Data Index: 23336 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1002361 (The Pile)

Max Activating Token Index: 694

Text #4

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.1334. Min Act: -0.0000

Data Index: 1924259 (The Pile)

Max Activating Token Index: 218

Text #5

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.0198. Min Act: -0.0000

Data Index: 1051409 (The Pile)

Max Activating Token Index: 948

Text #6

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.2227. Min Act: -0.0000

Data Index: 392784 (The Pile)

Max Activating Token Index: 39

Text #7

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.0312. Min Act: -0.0000

Data Index: 1821940 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.0658. Min Act: -0.0000

Data Index: 16948 (The Pile)

Max Activating Token Index: 876

Text #9

Max Range: 1.4774. Min Range: -1.4774

Max Act: 0.9866. Min Act: -0.0000

Data Index: 1927186 (The Pile)

Max Activating Token Index: 814

Text #10

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.1167. Min Act: -0.0000

Data Index: 580718 (The Pile)

Max Activating Token Index: 489

Text #11

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.0696. Min Act: -0.0000

Data Index: 1543544 (The Pile)

Max Activating Token Index: 547

Text #12

Max Range: 1.4774. Min Range: -1.4774

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1560114 (The Pile)

Max Activating Token Index: 110

Text #13

Max Range: 1.4774. Min Range: -1.4774

Max Act: 0.9580. Min Act: -0.0000

Data Index: 1344785 (The Pile)

Max Activating Token Index: 693

Text #14

Max Range: 1.4774. Min Range: -1.4774

Max Act: 0.9826. Min Act: -0.0000

Data Index: 1094500 (The Pile)

Max Activating Token Index: 335

Text #15

Max Range: 1.4774. Min Range: -1.4774

Max Act: 0.9500. Min Act: -0.0000

Data Index: 908863 (The Pile)

Max Activating Token Index: 810

Text #16

Max Range: 1.4774. Min Range: -1.4774

Max Act: 0.9860. Min Act: -0.0000

Data Index: 1353039 (The Pile)

Max Activating Token Index: 253

Text #17

Max Range: 1.4774. Min Range: -1.4774

Max Act: 0.9595. Min Act: -0.0000

Data Index: 120845 (The Pile)

Max Activating Token Index: 600

Text #18

Max Range: 1.4774. Min Range: -1.4774

Max Act: 0.9816. Min Act: -0.0000

Data Index: 1560106 (The Pile)

Max Activating Token Index: 762

Text #19

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.0151. Min Act: -0.0000

Data Index: 1376975 (The Pile)

Max Activating Token Index: 69