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

Dataset: The Pile

Neuron 2055 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: 1.6303. Min Range: -1.6303

Max Act: 1.3241. Min Act: -0.0000

Data Index: 503026 (The Pile)

Max Activating Token Index: 382

Text #1

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.5660. Min Act: -0.0000

Data Index: 853080 (The Pile)

Max Activating Token Index: 216

Text #2

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.3885. Min Act: -0.0000

Data Index: 931686 (The Pile)

Max Activating Token Index: 317

Text #3

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.6303. Min Act: -0.0000

Data Index: 1692760 (The Pile)

Max Activating Token Index: 83

Text #4

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.5194. Min Act: -0.0000

Data Index: 364292 (The Pile)

Max Activating Token Index: 830

Text #5

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.3456. Min Act: -0.0000

Data Index: 189377 (The Pile)

Max Activating Token Index: 971

Text #6

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.3689. Min Act: -0.0000

Data Index: 1935958 (The Pile)

Max Activating Token Index: 416

Text #7

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.4591. Min Act: -0.0000

Data Index: 228034 (The Pile)

Max Activating Token Index: 275

Text #8

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.2645. Min Act: -0.0001

Data Index: 773891 (The Pile)

Max Activating Token Index: 309

Text #9

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.2341. Min Act: -0.0000

Data Index: 963217 (The Pile)

Max Activating Token Index: 445

Text #10

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.1884. Min Act: -0.0000

Data Index: 1444076 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.1775. Min Act: -0.0000

Data Index: 466844 (The Pile)

Max Activating Token Index: 462

Text #12

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.2122. Min Act: -0.0000

Data Index: 454678 (The Pile)

Max Activating Token Index: 34

Text #13

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.1894. Min Act: -0.0000

Data Index: 956742 (The Pile)

Max Activating Token Index: 744

Text #14

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.1421. Min Act: -0.0000

Data Index: 1334190 (The Pile)

Max Activating Token Index: 599

Text #15

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.2053. Min Act: -0.0000

Data Index: 1667625 (The Pile)

Max Activating Token Index: 539

Text #16

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.1986. Min Act: -0.0000

Data Index: 1893988 (The Pile)

Max Activating Token Index: 301

Text #17

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.1470. Min Act: -0.0000

Data Index: 155824 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.1454. Min Act: -0.0000

Data Index: 834837 (The Pile)

Max Activating Token Index: 180

Text #19

Max Range: 1.6303. Min Range: -1.6303

Max Act: 1.1803. Min Act: -0.0000

Data Index: 1281702 (The Pile)

Max Activating Token Index: 225