Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1982 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.0973. Min Range: -3.0973

Max Act: 3.0973. Min Act: -0.1700

Data Index: 1259016 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 3.0973. Min Range: -3.0973

Max Act: 3.0658. Min Act: -0.1700

Data Index: 657430 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 3.0973. Min Range: -3.0973

Max Act: 3.0026. Min Act: -0.1700

Data Index: 616538 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 3.0973. Min Range: -3.0973

Max Act: 3.0184. Min Act: -0.1700

Data Index: 980221 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 3.0973. Min Range: -3.0973

Max Act: 3.0026. Min Act: -0.1700

Data Index: 1221171 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 3.0973. Min Range: -3.0973

Max Act: 3.0026. Min Act: -0.1700

Data Index: 396805 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9551. Min Act: -0.1700

Data Index: 1154973 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9868. Min Act: -0.1700

Data Index: 518948 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9551. Min Act: -0.1700

Data Index: 29142 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9710. Min Act: -0.1700

Data Index: 264886 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9710. Min Act: -0.1700

Data Index: 347947 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9551. Min Act: -0.1700

Data Index: 871909 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9710. Min Act: -0.1700

Data Index: 588978 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9710. Min Act: -0.1700

Data Index: 325959 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9710. Min Act: -0.1700

Data Index: 70768 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9235. Min Act: -0.1700

Data Index: 204663 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9710. Min Act: -0.1700

Data Index: 64237 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9551. Min Act: -0.1700

Data Index: 634258 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9393. Min Act: -0.1700

Data Index: 1185674 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 3.0973. Min Range: -3.0973

Max Act: 2.9076. Min Act: -0.1700

Data Index: 1040589 (C4 (Web Text))

Max Activating Token Index: 573