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

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

Neuron 1874 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: 4.2307. Min Range: -4.2307

Max Act: 4.2307. Min Act: -0.1700

Data Index: 658639 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 4.2307. Min Range: -4.2307

Max Act: 3.9806. Min Act: -0.1700

Data Index: 191070 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 4.2307. Min Range: -4.2307

Max Act: 4.0744. Min Act: -0.1700

Data Index: 1071706 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 4.2307. Min Range: -4.2307

Max Act: 4.0119. Min Act: -0.1700

Data Index: 883416 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 4.2307. Min Range: -4.2307

Max Act: 3.9806. Min Act: -0.1700

Data Index: 807658 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 4.2307. Min Range: -4.2307

Max Act: 3.9806. Min Act: -0.1700

Data Index: 893492 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 4.2307. Min Range: -4.2307

Max Act: 3.9493. Min Act: -0.1700

Data Index: 235897 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 4.2307. Min Range: -4.2307

Max Act: 3.9493. Min Act: -0.1700

Data Index: 47182 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 4.2307. Min Range: -4.2307

Max Act: 3.9493. Min Act: -0.1700

Data Index: 333190 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 4.2307. Min Range: -4.2307

Max Act: 3.9493. Min Act: -0.1700

Data Index: 814783 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 4.2307. Min Range: -4.2307

Max Act: 3.9493. Min Act: -0.1700

Data Index: 938770 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 4.2307. Min Range: -4.2307

Max Act: 3.9493. Min Act: -0.1700

Data Index: 85832 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 4.2307. Min Range: -4.2307

Max Act: 3.9180. Min Act: -0.1700

Data Index: 144564 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 4.2307. Min Range: -4.2307

Max Act: 3.9180. Min Act: -0.1700

Data Index: 463116 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 4.2307. Min Range: -4.2307

Max Act: 3.8555. Min Act: -0.1700

Data Index: 598093 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 4.2307. Min Range: -4.2307

Max Act: 3.8868. Min Act: -0.1700

Data Index: 1204827 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 4.2307. Min Range: -4.2307

Max Act: 3.9180. Min Act: -0.1700

Data Index: 870268 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 4.2307. Min Range: -4.2307

Max Act: 3.8555. Min Act: -0.1700

Data Index: 315969 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 4.2307. Min Range: -4.2307

Max Act: 3.8555. Min Act: -0.1700

Data Index: 7536 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 4.2307. Min Range: -4.2307

Max Act: 3.8242. Min Act: -0.1700

Data Index: 637730 (C4 (Web Text))

Max Activating Token Index: 26