Model: GELU Model: 2 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 8 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.0773. Min Range: -5.0773

Max Act: 5.0773. Min Act: -0.1700

Data Index: 1185211 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 5.0773. Min Range: -5.0773

Max Act: 5.0148. Min Act: -0.1700

Data Index: 348650 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 5.0773. Min Range: -5.0773

Max Act: 5.0148. Min Act: -0.1700

Data Index: 79158 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 5.0773. Min Range: -5.0773

Max Act: 4.9367. Min Act: -0.1700

Data Index: 802972 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 5.0773. Min Range: -5.0773

Max Act: 4.9836. Min Act: -0.1700

Data Index: 267554 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 5.0773. Min Range: -5.0773

Max Act: 4.9836. Min Act: -0.1700

Data Index: 718335 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 5.0773. Min Range: -5.0773

Max Act: 4.8742. Min Act: -0.1700

Data Index: 227573 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 5.0773. Min Range: -5.0773

Max Act: 4.9211. Min Act: -0.1700

Data Index: 480494 (C4 (Web Text))

Max Activating Token Index: 730

Text #8

Max Range: 5.0773. Min Range: -5.0773

Max Act: 4.9367. Min Act: -0.1700

Data Index: 1041715 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 5.0773. Min Range: -5.0773

Max Act: 4.9055. Min Act: -0.1700

Data Index: 780620 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 5.0773. Min Range: -5.0773

Max Act: 4.9055. Min Act: -0.1700

Data Index: 161531 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 5.0773. Min Range: -5.0773

Max Act: 4.9055. Min Act: -0.1700

Data Index: 116557 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 5.0773. Min Range: -5.0773

Max Act: 4.8742. Min Act: -0.1700

Data Index: 87944 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 5.0773. Min Range: -5.0773

Max Act: 4.8898. Min Act: -0.1700

Data Index: 740785 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 5.0773. Min Range: -5.0773

Max Act: 4.9055. Min Act: -0.1700

Data Index: 80646 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 5.0773. Min Range: -5.0773

Max Act: 4.9055. Min Act: -0.1700

Data Index: 765597 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 5.0773. Min Range: -5.0773

Max Act: 4.8586. Min Act: -0.1700

Data Index: 1006656 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 5.0773. Min Range: -5.0773

Max Act: 4.9055. Min Act: -0.1700

Data Index: 431224 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 5.0773. Min Range: -5.0773

Max Act: 4.8898. Min Act: -0.1700

Data Index: 1154114 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 5.0773. Min Range: -5.0773

Max Act: 4.8117. Min Act: -0.1700

Data Index: 408696 (C4 (Web Text))

Max Activating Token Index: 129