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

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

Neuron 908 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: 3.2512. Min Range: -3.2512

Max Act: 3.2512. Min Act: -0.1700

Data Index: 1565300 (Python Code)

Max Activating Token Index: 968

Text #1

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.1735. Min Act: -0.1695

Data Index: 24605 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.1869. Min Act: -0.1546

Data Index: 1383954 (Python Code)

Max Activating Token Index: 880

Text #3

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.1365. Min Act: -0.1690

Data Index: 1159809 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.1205. Min Act: -0.1698

Data Index: 1275321 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.1049. Min Act: -0.1539

Data Index: 1391449 (Python Code)

Max Activating Token Index: 677

Text #6

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.0645. Min Act: -0.1538

Data Index: 1172034 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.0417. Min Act: -0.1700

Data Index: 1501918 (Python Code)

Max Activating Token Index: 237

Text #8

Max Range: 3.2512. Min Range: -3.2512

Max Act: 3.0281. Min Act: -0.1700

Data Index: 98042 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.9879. Min Act: -0.1700

Data Index: 1624629 (Python Code)

Max Activating Token Index: 814

Text #10

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.9775. Min Act: -0.1400

Data Index: 202715 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.9734. Min Act: -0.1696

Data Index: 1640007 (Python Code)

Max Activating Token Index: 623

Text #12

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.9743. Min Act: -0.1552

Data Index: 1576116 (Python Code)

Max Activating Token Index: 485

Text #13

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.9612. Min Act: -0.1699

Data Index: 1392547 (Python Code)

Max Activating Token Index: 304

Text #14

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.9441. Min Act: -0.1700

Data Index: 936354 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.9421. Min Act: -0.1699

Data Index: 279793 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.9440. Min Act: -0.1699

Data Index: 754124 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.9329. Min Act: -0.1649

Data Index: 1622311 (Python Code)

Max Activating Token Index: 597

Text #18

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.9378. Min Act: -0.1700

Data Index: 1009017 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 3.2512. Min Range: -3.2512

Max Act: 2.9323. Min Act: -0.1696

Data Index: 711451 (C4 (Web Text))

Max Activating Token Index: 275