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

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

Neuron 1558 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: 3.2390. Min Range: -3.2390

Max Act: 3.2390. Min Act: -0.1700

Data Index: 915182 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1932. Min Act: -0.1700

Data Index: 158610 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1442. Min Act: -0.1700

Data Index: 968726 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1292. Min Act: -0.1700

Data Index: 635480 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1059. Min Act: -0.1700

Data Index: 793336 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1060. Min Act: -0.1700

Data Index: 16332 (C4 (Web Text))

Max Activating Token Index: 485

Text #6

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1002. Min Act: -0.1700

Data Index: 29927 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1145. Min Act: -0.1700

Data Index: 961901 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1106. Min Act: -0.1700

Data Index: 458319 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.0854. Min Act: -0.1700

Data Index: 450835 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.0667. Min Act: -0.1700

Data Index: 635358 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.0744. Min Act: -0.1700

Data Index: 131879 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.0793. Min Act: -0.1700

Data Index: 874518 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.0469. Min Act: -0.1700

Data Index: 503512 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.0388. Min Act: -0.1699

Data Index: 1164183 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.0349. Min Act: -0.1700

Data Index: 575511 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.0366. Min Act: -0.1700

Data Index: 1066798 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.0368. Min Act: -0.1700

Data Index: 606820 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.0284. Min Act: -0.1700

Data Index: 212338 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.0238. Min Act: -0.1700

Data Index: 131527 (C4 (Web Text))

Max Activating Token Index: 909