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

Dataset: The Pile

Neuron 2451 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: 0.5677. Min Range: -0.5677

Max Act: 0.5677. Min Act: -0.0000

Data Index: 667797 (The Pile)

Max Activating Token Index: 786

Text #1

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1321978 (The Pile)

Max Activating Token Index: 696

Text #2

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.5495. Min Act: -0.0000

Data Index: 882777 (The Pile)

Max Activating Token Index: 875

Text #3

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1747020 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.5352. Min Act: -0.0000

Data Index: 945240 (The Pile)

Max Activating Token Index: 708

Text #5

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4791. Min Act: -0.0000

Data Index: 185640 (The Pile)

Max Activating Token Index: 191

Text #6

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1499666 (The Pile)

Max Activating Token Index: 774

Text #7

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4424. Min Act: -0.0000

Data Index: 259831 (The Pile)

Max Activating Token Index: 442

Text #8

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4285. Min Act: -0.0000

Data Index: 1717845 (The Pile)

Max Activating Token Index: 8

Text #9

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1663466 (The Pile)

Max Activating Token Index: 127

Text #10

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3983. Min Act: -0.0000

Data Index: 1800009 (The Pile)

Max Activating Token Index: 336

Text #11

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4231. Min Act: -0.0000

Data Index: 499643 (The Pile)

Max Activating Token Index: 801

Text #12

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3968. Min Act: -0.0000

Data Index: 285268 (The Pile)

Max Activating Token Index: 939

Text #13

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3952. Min Act: -0.0000

Data Index: 187447 (The Pile)

Max Activating Token Index: 770

Text #14

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4027. Min Act: -0.0000

Data Index: 1513921 (The Pile)

Max Activating Token Index: 355

Text #15

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4474. Min Act: -0.0000

Data Index: 764941 (The Pile)

Max Activating Token Index: 445

Text #16

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3883. Min Act: -0.0000

Data Index: 205129 (The Pile)

Max Activating Token Index: 25

Text #17

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4397. Min Act: -0.0000

Data Index: 437682 (The Pile)

Max Activating Token Index: 634

Text #18

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.3727. Min Act: -0.0000

Data Index: 990038 (The Pile)

Max Activating Token Index: 471

Text #19

Max Range: 0.5677. Min Range: -0.5677

Max Act: 0.4246. Min Act: -0.0000

Data Index: 1940655 (The Pile)

Max Activating Token Index: 985