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

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

Neuron 452 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: 4.4810. Min Range: -4.4810

Max Act: 4.4810. Min Act: -0.1699

Data Index: 329718 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 4.4810. Min Range: -4.4810

Max Act: 4.1971. Min Act: -0.1700

Data Index: 1014654 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 4.4810. Min Range: -4.4810

Max Act: 4.1184. Min Act: -0.1700

Data Index: 431257 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 4.4810. Min Range: -4.4810

Max Act: 3.8842. Min Act: -0.1700

Data Index: 94668 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 4.4810. Min Range: -4.4810

Max Act: 3.9061. Min Act: -0.1700

Data Index: 1075223 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 4.4810. Min Range: -4.4810

Max Act: 3.8518. Min Act: -0.1700

Data Index: 1652688 (Python Code)

Max Activating Token Index: 793

Text #6

Max Range: 4.4810. Min Range: -4.4810

Max Act: 3.8366. Min Act: -0.1700

Data Index: 317586 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 4.4810. Min Range: -4.4810

Max Act: 3.7886. Min Act: -0.1700

Data Index: 801760 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 4.4810. Min Range: -4.4810

Max Act: 3.7565. Min Act: -0.1700

Data Index: 227633 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 4.4810. Min Range: -4.4810

Max Act: 3.7772. Min Act: -0.1698

Data Index: 966338 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 4.4810. Min Range: -4.4810

Max Act: 3.7539. Min Act: -0.1699

Data Index: 1067629 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 4.4810. Min Range: -4.4810

Max Act: 3.7482. Min Act: -0.1700

Data Index: 702030 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 4.4810. Min Range: -4.4810

Max Act: 3.7453. Min Act: -0.1697

Data Index: 1454200 (Python Code)

Max Activating Token Index: 854

Text #13

Max Range: 4.4810. Min Range: -4.4810

Max Act: 3.7699. Min Act: -0.1698

Data Index: 1545391 (Python Code)

Max Activating Token Index: 808

Text #14

Max Range: 4.4810. Min Range: -4.4810

Max Act: 3.7093. Min Act: -0.1694

Data Index: 1369199 (Python Code)

Max Activating Token Index: 256

Text #15

Max Range: 4.4810. Min Range: -4.4810

Max Act: 3.7289. Min Act: -0.1689

Data Index: 1533404 (Python Code)

Max Activating Token Index: 437

Text #16

Max Range: 4.4810. Min Range: -4.4810

Max Act: 3.7216. Min Act: -0.1699

Data Index: 1454172 (Python Code)

Max Activating Token Index: 574

Text #17

Max Range: 4.4810. Min Range: -4.4810

Max Act: 3.7219. Min Act: -0.1700

Data Index: 763764 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 4.4810. Min Range: -4.4810

Max Act: 3.7194. Min Act: -0.1700

Data Index: 840796 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 4.4810. Min Range: -4.4810

Max Act: 3.6984. Min Act: -0.1699

Data Index: 113879 (C4 (Web Text))

Max Activating Token Index: 956