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

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

Neuron 1991 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: 4.2702. Min Range: -4.2702

Max Act: 4.2702. Min Act: -0.1665

Data Index: 838373 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.2171. Min Act: -0.1700

Data Index: 670494 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.1965. Min Act: -0.1700

Data Index: 402480 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.1709. Min Act: -0.1700

Data Index: 1358536 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.1315. Min Act: -0.1700

Data Index: 1097146 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.1325. Min Act: -0.1700

Data Index: 266940 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.1231. Min Act: -0.1700

Data Index: 847393 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.0971. Min Act: -0.1700

Data Index: 183983 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.1268. Min Act: -0.1700

Data Index: 567502 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.1140. Min Act: -0.1700

Data Index: 296467 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.0731. Min Act: -0.1700

Data Index: 276813 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.0719. Min Act: -0.1700

Data Index: 708509 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.0872. Min Act: -0.1700

Data Index: 959751 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.0973. Min Act: -0.1700

Data Index: 1334367 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.0964. Min Act: -0.1689

Data Index: 113088 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.0360. Min Act: -0.1700

Data Index: 1095822 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.0421. Min Act: -0.1700

Data Index: 71045 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.0511. Min Act: -0.1700

Data Index: 370836 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.0559. Min Act: -0.1700

Data Index: 234861 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.0469. Min Act: -0.1700

Data Index: 389200 (C4 (Web Text))

Max Activating Token Index: 152