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

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

Neuron 1142 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: 3.0674. Min Range: -3.0674

Max Act: 3.0674. Min Act: -0.0171

Data Index: 824268 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 3.0674. Min Range: -3.0674

Max Act: 3.0555. Min Act: -0.1697

Data Index: 814648 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 3.0674. Min Range: -3.0674

Max Act: 3.0171. Min Act: -0.1700

Data Index: 580370 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 3.0674. Min Range: -3.0674

Max Act: 3.0095. Min Act: -0.1696

Data Index: 63976 (C4 (Web Text))

Max Activating Token Index: 319

Text #4

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.9543. Min Act: -0.1700

Data Index: 656151 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.9571. Min Act: -0.1682

Data Index: 177189 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.9367. Min Act: -0.1670

Data Index: 246225 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.9345. Min Act: -0.1700

Data Index: 600796 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.9242. Min Act: -0.1698

Data Index: 766588 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.9304. Min Act: -0.1479

Data Index: 724812 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.9172. Min Act: -0.1606

Data Index: 1262742 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.9268. Min Act: -0.1700

Data Index: 501440 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.9242. Min Act: -0.1691

Data Index: 789656 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.9121. Min Act: -0.1614

Data Index: 416973 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.9117. Min Act: -0.1617

Data Index: 123600 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.9121. Min Act: -0.1699

Data Index: 603991 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.8849. Min Act: -0.1683

Data Index: 220180 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.8974. Min Act: -0.1700

Data Index: 445266 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.8904. Min Act: -0.1698

Data Index: 83383 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 3.0674. Min Range: -3.0674

Max Act: 2.9014. Min Act: -0.1261

Data Index: 907174 (C4 (Web Text))

Max Activating Token Index: 211