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

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

Neuron 1546 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: 5.2477. Min Range: -5.2477

Max Act: 5.2477. Min Act: -0.1699

Data Index: 760593 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.7477. Min Act: -0.1700

Data Index: 367872 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.7164. Min Act: -0.1700

Data Index: 941276 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.6852. Min Act: -0.1535

Data Index: 828517 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.6852. Min Act: -0.1700

Data Index: 1357888 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.8102. Min Act: -0.1700

Data Index: 1068722 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.6539. Min Act: -0.1700

Data Index: 880061 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.6539. Min Act: -0.1700

Data Index: 1270753 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.6852. Min Act: -0.1684

Data Index: 969216 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.6227. Min Act: -0.1700

Data Index: 998183 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.6227. Min Act: -0.1700

Data Index: 218114 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.5914. Min Act: -0.1700

Data Index: 324884 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.6227. Min Act: -0.1691

Data Index: 385370 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.5914. Min Act: -0.1700

Data Index: 190851 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.6227. Min Act: -0.1700

Data Index: 840085 (C4 (Web Text))

Max Activating Token Index: 637

Text #15

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.5602. Min Act: -0.1700

Data Index: 732223 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.5289. Min Act: -0.1700

Data Index: 578651 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.5289. Min Act: -0.1700

Data Index: 722603 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.5289. Min Act: -0.1700

Data Index: 211125 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.5289. Min Act: -0.1700

Data Index: 1234141 (C4 (Web Text))

Max Activating Token Index: 575