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

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

Neuron 647 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: 3.8473. Min Range: -3.8473

Max Act: 3.8473. Min Act: -0.1700

Data Index: 1195204 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 3.8473. Min Range: -3.8473

Max Act: 3.7746. Min Act: -0.1700

Data Index: 725001 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 3.8473. Min Range: -3.8473

Max Act: 3.7870. Min Act: -0.1700

Data Index: 1279768 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 3.8473. Min Range: -3.8473

Max Act: 3.7625. Min Act: -0.1700

Data Index: 658582 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 3.8473. Min Range: -3.8473

Max Act: 3.7447. Min Act: -0.1700

Data Index: 484768 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 3.8473. Min Range: -3.8473

Max Act: 3.7386. Min Act: -0.1700

Data Index: 1061897 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 3.8473. Min Range: -3.8473

Max Act: 3.7406. Min Act: -0.1700

Data Index: 253933 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 3.8473. Min Range: -3.8473

Max Act: 3.7610. Min Act: -0.1700

Data Index: 518928 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 3.8473. Min Range: -3.8473

Max Act: 3.7538. Min Act: -0.1700

Data Index: 158750 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 3.8473. Min Range: -3.8473

Max Act: 3.7269. Min Act: -0.1700

Data Index: 1222273 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 3.8473. Min Range: -3.8473

Max Act: 3.7786. Min Act: -0.1700

Data Index: 113964 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 3.8473. Min Range: -3.8473

Max Act: 3.7373. Min Act: -0.1700

Data Index: 422978 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 3.8473. Min Range: -3.8473

Max Act: 3.7485. Min Act: -0.1700

Data Index: 1243376 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 3.8473. Min Range: -3.8473

Max Act: 3.7315. Min Act: -0.1700

Data Index: 1245697 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 3.8473. Min Range: -3.8473

Max Act: 3.7144. Min Act: -0.1700

Data Index: 173814 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 3.8473. Min Range: -3.8473

Max Act: 3.7398. Min Act: -0.1700

Data Index: 460109 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 3.8473. Min Range: -3.8473

Max Act: 3.7157. Min Act: -0.1700

Data Index: 177510 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 3.8473. Min Range: -3.8473

Max Act: 3.6854. Min Act: -0.1700

Data Index: 903709 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 3.8473. Min Range: -3.8473

Max Act: 3.7214. Min Act: -0.1700

Data Index: 694425 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 3.8473. Min Range: -3.8473

Max Act: 3.7142. Min Act: -0.1700

Data Index: 1114269 (C4 (Web Text))

Max Activating Token Index: 308