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

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

Neuron 19 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: 5.8122. Min Range: -5.8122

Max Act: 5.8122. Min Act: -0.1700

Data Index: 680010 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 5.8122. Min Range: -5.8122

Max Act: 5.4685. Min Act: -0.1700

Data Index: 232853 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 5.8122. Min Range: -5.8122

Max Act: 5.3747. Min Act: -0.1700

Data Index: 1095488 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 5.8122. Min Range: -5.8122

Max Act: 5.3747. Min Act: -0.1700

Data Index: 1263204 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 5.8122. Min Range: -5.8122

Max Act: 5.3747. Min Act: -0.1700

Data Index: 262198 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 5.8122. Min Range: -5.8122

Max Act: 5.4372. Min Act: -0.1700

Data Index: 1019569 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 5.8122. Min Range: -5.8122

Max Act: 5.3747. Min Act: -0.1700

Data Index: 610473 (C4 (Web Text))

Max Activating Token Index: 648

Text #7

Max Range: 5.8122. Min Range: -5.8122

Max Act: 5.3435. Min Act: -0.1700

Data Index: 859105 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 5.8122. Min Range: -5.8122

Max Act: 5.3747. Min Act: -0.1700

Data Index: 1123668 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 5.8122. Min Range: -5.8122

Max Act: 5.2810. Min Act: -0.1699

Data Index: 578918 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 5.8122. Min Range: -5.8122

Max Act: 5.3435. Min Act: -0.1700

Data Index: 1086508 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 5.8122. Min Range: -5.8122

Max Act: 5.2497. Min Act: -0.1700

Data Index: 1153379 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 5.8122. Min Range: -5.8122

Max Act: 5.1872. Min Act: -0.1700

Data Index: 519895 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 5.8122. Min Range: -5.8122

Max Act: 5.2497. Min Act: -0.1700

Data Index: 1147303 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 5.8122. Min Range: -5.8122

Max Act: 5.2810. Min Act: -0.1700

Data Index: 385876 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 5.8122. Min Range: -5.8122

Max Act: 5.2810. Min Act: -0.1700

Data Index: 341340 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 5.8122. Min Range: -5.8122

Max Act: 5.2497. Min Act: -0.1700

Data Index: 193555 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 5.8122. Min Range: -5.8122

Max Act: 5.2185. Min Act: -0.1696

Data Index: 957699 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 5.8122. Min Range: -5.8122

Max Act: 5.1872. Min Act: -0.1700

Data Index: 89421 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 5.8122. Min Range: -5.8122

Max Act: 5.2497. Min Act: -0.1700

Data Index: 153507 (C4 (Web Text))

Max Activating Token Index: 739