Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 313 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.5612. Min Range: -5.5612

Max Act: 5.5612. Min Act: -0.1700

Data Index: 1304104 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 5.5612. Min Range: -5.5612

Max Act: 5.4362. Min Act: -0.1700

Data Index: 1039388 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 5.5612. Min Range: -5.5612

Max Act: 5.3424. Min Act: -0.1700

Data Index: 5526 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 5.5612. Min Range: -5.5612

Max Act: 5.2487. Min Act: -0.1700

Data Index: 1011682 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 5.5612. Min Range: -5.5612

Max Act: 5.2487. Min Act: -0.1700

Data Index: 1318033 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 5.5612. Min Range: -5.5612

Max Act: 5.2487. Min Act: -0.1700

Data Index: 1344502 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 5.5612. Min Range: -5.5612

Max Act: 5.2799. Min Act: -0.1700

Data Index: 651407 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 5.5612. Min Range: -5.5612

Max Act: 5.2487. Min Act: -0.1700

Data Index: 181400 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 5.5612. Min Range: -5.5612

Max Act: 5.2487. Min Act: -0.1700

Data Index: 533012 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 5.5612. Min Range: -5.5612

Max Act: 5.1549. Min Act: -0.1700

Data Index: 1309833 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 5.5612. Min Range: -5.5612

Max Act: 5.1549. Min Act: -0.1700

Data Index: 996741 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 5.5612. Min Range: -5.5612

Max Act: 5.0924. Min Act: -0.1700

Data Index: 1103708 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 5.5612. Min Range: -5.5612

Max Act: 5.0612. Min Act: -0.1700

Data Index: 788299 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 5.5612. Min Range: -5.5612

Max Act: 5.0612. Min Act: -0.1700

Data Index: 290944 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 5.5612. Min Range: -5.5612

Max Act: 5.0612. Min Act: -0.1700

Data Index: 1312765 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 5.5612. Min Range: -5.5612

Max Act: 4.9362. Min Act: -0.1700

Data Index: 380853 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 5.5612. Min Range: -5.5612

Max Act: 4.9987. Min Act: -0.1700

Data Index: 578465 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 5.5612. Min Range: -5.5612

Max Act: 5.0299. Min Act: -0.1700

Data Index: 380766 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 5.5612. Min Range: -5.5612

Max Act: 4.9049. Min Act: -0.1700

Data Index: 418612 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 5.5612. Min Range: -5.5612

Max Act: 4.9674. Min Act: -0.1700

Data Index: 725539 (C4 (Web Text))

Max Activating Token Index: 15