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

Dataset: The Pile

Neuron 2560 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: 2.4397. Min Range: -2.4397

Max Act: 2.4397. Min Act: -0.0000

Data Index: 1324887 (The Pile)

Max Activating Token Index: 185

Text #1

Max Range: 2.4397. Min Range: -2.4397

Max Act: 1.8366. Min Act: 0.0000

Data Index: 1926551 (The Pile)

Max Activating Token Index: 83

Text #2

Max Range: 2.4397. Min Range: -2.4397

Max Act: 1.6472. Min Act: -0.0000

Data Index: 1128743 (The Pile)

Max Activating Token Index: 588

Text #3

Max Range: 2.4397. Min Range: -2.4397

Max Act: 1.7352. Min Act: -0.0000

Data Index: 276392 (The Pile)

Max Activating Token Index: 26

Text #4

Max Range: 2.4397. Min Range: -2.4397

Max Act: 1.6823. Min Act: -0.0000

Data Index: 123720 (The Pile)

Max Activating Token Index: 960

Text #5

Max Range: 2.4397. Min Range: -2.4397

Max Act: 1.4952. Min Act: -0.0000

Data Index: 1653765 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 2.4397. Min Range: -2.4397

Max Act: 1.5622. Min Act: -0.0000

Data Index: 1124690 (The Pile)

Max Activating Token Index: 841

Text #7

Max Range: 2.4397. Min Range: -2.4397

Max Act: 1.6442. Min Act: -0.0000

Data Index: 960579 (The Pile)

Max Activating Token Index: 422

Text #8

Max Range: 2.4397. Min Range: -2.4397

Max Act: 1.4432. Min Act: -0.0000

Data Index: 1495673 (The Pile)

Max Activating Token Index: 201

Text #9

Max Range: 2.4397. Min Range: -2.4397

Max Act: 1.5962. Min Act: 0.0000

Data Index: 1232938 (The Pile)

Max Activating Token Index: 191

Text #10

Max Range: 2.4397. Min Range: -2.4397

Max Act: 1.5727. Min Act: -0.0000

Data Index: 1118792 (The Pile)

Max Activating Token Index: 94

Text #11

Max Range: 2.4397. Min Range: -2.4397

Max Act: 1.4622. Min Act: -0.0000

Data Index: 1515817 (The Pile)

Max Activating Token Index: 371

Text #12

Max Range: 2.4397. Min Range: -2.4397

Max Act: 1.4248. Min Act: -0.0000

Data Index: 1331780 (The Pile)

Max Activating Token Index: 38

Text #13

Max Range: 2.4397. Min Range: -2.4397

Max Act: 1.4040. Min Act: -0.0000

Data Index: 130567 (The Pile)

Max Activating Token Index: 406

Text #14

Max Range: 2.4397. Min Range: -2.4397

Max Act: 1.4923. Min Act: -0.0000

Data Index: 978399 (The Pile)

Max Activating Token Index: 39

Text #15

Max Range: 2.4397. Min Range: -2.4397

Max Act: 1.4968. Min Act: -0.0000

Data Index: 824611 (The Pile)

Max Activating Token Index: 733

Text #16

Max Range: 2.4397. Min Range: -2.4397

Max Act: 1.4732. Min Act: -0.0000

Data Index: 1521299 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 2.4397. Min Range: -2.4397

Max Act: 1.4712. Min Act: -0.0000

Data Index: 1082327 (The Pile)

Max Activating Token Index: 671

Text #18

Max Range: 2.4397. Min Range: -2.4397

Max Act: 1.3743. Min Act: -0.0000

Data Index: 1908847 (The Pile)

Max Activating Token Index: 315

Text #19

Max Range: 2.4397. Min Range: -2.4397

Max Act: 1.4680. Min Act: -0.0000

Data Index: 453281 (The Pile)

Max Activating Token Index: 78