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

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

Neuron 1858 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.2005. Min Act: -0.1700

Data Index: 401745 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.2319. Min Act: -0.1700

Data Index: 263871 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.1533. Min Act: -0.1700

Data Index: 1153519 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.1533. Min Act: -0.1700

Data Index: 1012570 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.1690. Min Act: -0.1700

Data Index: 1248813 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.1375. Min Act: -0.1700

Data Index: 451535 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.1375. Min Act: -0.1700

Data Index: 1304566 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.1218. Min Act: -0.1700

Data Index: 53767 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.1060. Min Act: -0.1700

Data Index: 517319 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.1060. Min Act: -0.1700

Data Index: 546950 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.1060. Min Act: -0.1700

Data Index: 570056 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.0902. Min Act: -0.1700

Data Index: 696635 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.0902. Min Act: -0.1700

Data Index: 1088581 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.0902. Min Act: -0.1700

Data Index: 61635 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.0429. Min Act: -0.1700

Data Index: 942062 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.0744. Min Act: -0.1700

Data Index: 179951 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.0744. Min Act: -0.1700

Data Index: 271024 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.0744. Min Act: -0.1700

Data Index: 51482 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.0744. Min Act: -0.1700

Data Index: 1185181 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 3.2319. Min Range: -3.2319

Max Act: 3.0587. Min Act: -0.1700

Data Index: 451497 (C4 (Web Text))

Max Activating Token Index: 935