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

Dataset: The Pile

Neuron 1954 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2931. Min Range: -1.2931

Max Act: 1.2931. Min Act: -0.0000

Data Index: 992655 (The Pile)

Max Activating Token Index: 328

Text #1

Max Range: 1.2931. Min Range: -1.2931

Max Act: 1.2747. Min Act: -0.0000

Data Index: 1058837 (The Pile)

Max Activating Token Index: 859

Text #2

Max Range: 1.2931. Min Range: -1.2931

Max Act: 1.2481. Min Act: -0.0000

Data Index: 147687 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 1.2931. Min Range: -1.2931

Max Act: 1.2260. Min Act: -0.0000

Data Index: 1580725 (The Pile)

Max Activating Token Index: 174

Text #4

Max Range: 1.2931. Min Range: -1.2931

Max Act: 1.0942. Min Act: -0.0000

Data Index: 1850317 (The Pile)

Max Activating Token Index: 680

Text #5

Max Range: 1.2931. Min Range: -1.2931

Max Act: 1.1254. Min Act: -0.0000

Data Index: 137674 (The Pile)

Max Activating Token Index: 379

Text #6

Max Range: 1.2931. Min Range: -1.2931

Max Act: 1.1786. Min Act: -0.0000

Data Index: 161022 (The Pile)

Max Activating Token Index: 784

Text #7

Max Range: 1.2931. Min Range: -1.2931

Max Act: 1.0827. Min Act: -0.0000

Data Index: 113642 (The Pile)

Max Activating Token Index: 311

Text #8

Max Range: 1.2931. Min Range: -1.2931

Max Act: 1.0422. Min Act: -0.0000

Data Index: 179169 (The Pile)

Max Activating Token Index: 996

Text #9

Max Range: 1.2931. Min Range: -1.2931

Max Act: 1.0123. Min Act: -0.0000

Data Index: 667508 (The Pile)

Max Activating Token Index: 303

Text #10

Max Range: 1.2931. Min Range: -1.2931

Max Act: 1.0683. Min Act: -0.0000

Data Index: 1329932 (The Pile)

Max Activating Token Index: 93

Text #11

Max Range: 1.2931. Min Range: -1.2931

Max Act: 1.0572. Min Act: -0.0000

Data Index: 308733 (The Pile)

Max Activating Token Index: 59

Text #12

Max Range: 1.2931. Min Range: -1.2931

Max Act: 1.0588. Min Act: -0.0000

Data Index: 79003 (The Pile)

Max Activating Token Index: 122

Text #13

Max Range: 1.2931. Min Range: -1.2931

Max Act: 1.0063. Min Act: -0.0000

Data Index: 1398606 (The Pile)

Max Activating Token Index: 833

Text #14

Max Range: 1.2931. Min Range: -1.2931

Max Act: 1.0389. Min Act: -0.0000

Data Index: 1003912 (The Pile)

Max Activating Token Index: 32

Text #15

Max Range: 1.2931. Min Range: -1.2931

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1588497 (The Pile)

Max Activating Token Index: 608

Text #16

Max Range: 1.2931. Min Range: -1.2931

Max Act: 1.0271. Min Act: -0.0000

Data Index: 890625 (The Pile)

Max Activating Token Index: 684

Text #17

Max Range: 1.2931. Min Range: -1.2931

Max Act: 1.0229. Min Act: -0.0000

Data Index: 440576 (The Pile)

Max Activating Token Index: 356

Text #18

Max Range: 1.2931. Min Range: -1.2931

Max Act: 0.9980. Min Act: -0.0000

Data Index: 405337 (The Pile)

Max Activating Token Index: 200

Text #19

Max Range: 1.2931. Min Range: -1.2931

Max Act: 1.0795. Min Act: -0.0000

Data Index: 1624573 (The Pile)

Max Activating Token Index: 475