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

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

Neuron 879 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: 5.2451. Min Range: -5.2451

Max Act: 5.2451. Min Act: -0.1700

Data Index: 992883 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 5.2451. Min Range: -5.2451

Max Act: 5.2138. Min Act: -0.1700

Data Index: 292850 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 5.2451. Min Range: -5.2451

Max Act: 5.1826. Min Act: -0.1700

Data Index: 1254893 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 5.2451. Min Range: -5.2451

Max Act: 5.1201. Min Act: -0.1700

Data Index: 1052978 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 5.2451. Min Range: -5.2451

Max Act: 5.1513. Min Act: -0.1700

Data Index: 1255590 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 5.2451. Min Range: -5.2451

Max Act: 5.0888. Min Act: -0.1700

Data Index: 1275017 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 5.2451. Min Range: -5.2451

Max Act: 5.0888. Min Act: -0.1700

Data Index: 823750 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 5.2451. Min Range: -5.2451

Max Act: 5.1513. Min Act: -0.1700

Data Index: 419820 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 5.2451. Min Range: -5.2451

Max Act: 5.0576. Min Act: -0.1700

Data Index: 1124972 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 5.2451. Min Range: -5.2451

Max Act: 5.0888. Min Act: -0.1700

Data Index: 302798 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 5.2451. Min Range: -5.2451

Max Act: 5.1201. Min Act: -0.1700

Data Index: 1293112 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 5.2451. Min Range: -5.2451

Max Act: 5.0888. Min Act: -0.1700

Data Index: 794374 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 5.2451. Min Range: -5.2451

Max Act: 5.0576. Min Act: -0.1700

Data Index: 54793 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 5.2451. Min Range: -5.2451

Max Act: 5.0576. Min Act: -0.1700

Data Index: 1015375 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 5.2451. Min Range: -5.2451

Max Act: 5.0576. Min Act: -0.1700

Data Index: 534857 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 5.2451. Min Range: -5.2451

Max Act: 5.0576. Min Act: -0.1700

Data Index: 87738 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 5.2451. Min Range: -5.2451

Max Act: 5.0263. Min Act: -0.1700

Data Index: 730348 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 5.2451. Min Range: -5.2451

Max Act: 5.0263. Min Act: -0.1700

Data Index: 1110926 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 5.2451. Min Range: -5.2451

Max Act: 4.9951. Min Act: -0.1700

Data Index: 778649 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 5.2451. Min Range: -5.2451

Max Act: 5.0263. Min Act: -0.1700

Data Index: 212178 (C4 (Web Text))

Max Activating Token Index: 685