Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1985 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.6160. Min Act: -0.1700

Data Index: 169186 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.5994. Min Act: -0.1699

Data Index: 24874 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.5608. Min Act: -0.1700

Data Index: 1302470 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.5108. Min Act: -0.1700

Data Index: 1073173 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.4834. Min Act: -0.1700

Data Index: 143894 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.4318. Min Act: -0.1700

Data Index: 1249256 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.4359. Min Act: -0.1691

Data Index: 867468 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.4177. Min Act: -0.1700

Data Index: 814425 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.4225. Min Act: -0.1688

Data Index: 336958 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.4122. Min Act: -0.1698

Data Index: 904930 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.3873. Min Act: -0.1700

Data Index: 1267188 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.4153. Min Act: -0.1700

Data Index: 725124 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.3866. Min Act: -0.1700

Data Index: 1161184 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.3749. Min Act: -0.1700

Data Index: 541827 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.3854. Min Act: -0.1700

Data Index: 446838 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.3599. Min Act: -0.1700

Data Index: 165289 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.3568. Min Act: -0.1699

Data Index: 877648 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.3543. Min Act: -0.1700

Data Index: 1206367 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.3611. Min Act: -0.1698

Data Index: 929150 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 3.6160. Min Range: -3.6160

Max Act: 3.3494. Min Act: -0.1700

Data Index: 566945 (C4 (Web Text))

Max Activating Token Index: 309