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

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

Neuron 80 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: 6.1518. Min Range: -6.1518

Max Act: 6.1518. Min Act: -0.1700

Data Index: 1119541 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 6.1518. Min Range: -6.1518

Max Act: 5.8080. Min Act: -0.1700

Data Index: 336148 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 6.1518. Min Range: -6.1518

Max Act: 5.8080. Min Act: -0.1700

Data Index: 1166404 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 6.1518. Min Range: -6.1518

Max Act: 5.7455. Min Act: -0.1700

Data Index: 217095 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 6.1518. Min Range: -6.1518

Max Act: 5.6830. Min Act: -0.1699

Data Index: 571039 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 6.1518. Min Range: -6.1518

Max Act: 5.6830. Min Act: -0.1700

Data Index: 1169836 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 6.1518. Min Range: -6.1518

Max Act: 5.7455. Min Act: -0.1700

Data Index: 255846 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 6.1518. Min Range: -6.1518

Max Act: 5.6518. Min Act: -0.1697

Data Index: 877778 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 6.1518. Min Range: -6.1518

Max Act: 5.7143. Min Act: -0.1699

Data Index: 1061608 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 6.1518. Min Range: -6.1518

Max Act: 5.6205. Min Act: -0.1700

Data Index: 1297643 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 6.1518. Min Range: -6.1518

Max Act: 5.6518. Min Act: -0.1700

Data Index: 1199394 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 6.1518. Min Range: -6.1518

Max Act: 5.7143. Min Act: -0.1699

Data Index: 1159880 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 6.1518. Min Range: -6.1518

Max Act: 5.5893. Min Act: -0.1700

Data Index: 412138 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 6.1518. Min Range: -6.1518

Max Act: 5.5580. Min Act: -0.1700

Data Index: 905803 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 6.1518. Min Range: -6.1518

Max Act: 5.5580. Min Act: -0.1698

Data Index: 1351333 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 6.1518. Min Range: -6.1518

Max Act: 5.5580. Min Act: -0.1700

Data Index: 520408 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 6.1518. Min Range: -6.1518

Max Act: 5.5893. Min Act: -0.1693

Data Index: 676045 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 6.1518. Min Range: -6.1518

Max Act: 5.5893. Min Act: -0.1700

Data Index: 487072 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 6.1518. Min Range: -6.1518

Max Act: 5.5268. Min Act: -0.1695

Data Index: 312693 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 6.1518. Min Range: -6.1518

Max Act: 5.4330. Min Act: -0.1699

Data Index: 940865 (C4 (Web Text))

Max Activating Token Index: 798