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

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

Neuron 1163 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: 3.1588. Min Range: -3.1588

Max Act: 3.1588. Min Act: -0.1699

Data Index: 1317754 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 3.1588. Min Range: -3.1588

Max Act: 3.1526. Min Act: -0.1700

Data Index: 7480 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 3.1588. Min Range: -3.1588

Max Act: 3.1063. Min Act: -0.1598

Data Index: 762084 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 3.1588. Min Range: -3.1588

Max Act: 3.0210. Min Act: -0.1619

Data Index: 347797 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 3.1588. Min Range: -3.1588

Max Act: 2.9759. Min Act: -0.1700

Data Index: 360817 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 3.1588. Min Range: -3.1588

Max Act: 2.9813. Min Act: -0.1700

Data Index: 1178834 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 3.1588. Min Range: -3.1588

Max Act: 2.9751. Min Act: -0.1690

Data Index: 727341 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 3.1588. Min Range: -3.1588

Max Act: 2.9875. Min Act: -0.1699

Data Index: 615119 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 3.1588. Min Range: -3.1588

Max Act: 2.9625. Min Act: -0.1699

Data Index: 332102 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 3.1588. Min Range: -3.1588

Max Act: 2.9450. Min Act: -0.1700

Data Index: 1239242 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 3.1588. Min Range: -3.1588

Max Act: 2.9439. Min Act: -0.1700

Data Index: 577261 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 3.1588. Min Range: -3.1588

Max Act: 2.9439. Min Act: -0.1698

Data Index: 835417 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 3.1588. Min Range: -3.1588

Max Act: 2.9264. Min Act: -0.1526

Data Index: 538686 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 3.1588. Min Range: -3.1588

Max Act: 2.9384. Min Act: -0.1699

Data Index: 920876 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 3.1588. Min Range: -3.1588

Max Act: 2.9334. Min Act: -0.1681

Data Index: 690067 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 3.1588. Min Range: -3.1588

Max Act: 2.9345. Min Act: -0.1699

Data Index: 917404 (C4 (Web Text))

Max Activating Token Index: 511

Text #16

Max Range: 3.1588. Min Range: -3.1588

Max Act: 2.9228. Min Act: -0.1700

Data Index: 775021 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 3.1588. Min Range: -3.1588

Max Act: 2.9214. Min Act: -0.1700

Data Index: 496155 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 3.1588. Min Range: -3.1588

Max Act: 2.9249. Min Act: -0.1700

Data Index: 194671 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 3.1588. Min Range: -3.1588

Max Act: 2.9312. Min Act: -0.1700

Data Index: 209895 (C4 (Web Text))

Max Activating Token Index: 993