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

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

Neuron 968 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: 3.2716. Min Range: -3.2716

Max Act: 3.2716. Min Act: -0.1700

Data Index: 561810 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.2490. Min Act: -0.1700

Data Index: 1370877 (Python Code)

Max Activating Token Index: 708

Text #2

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.2327. Min Act: -0.1700

Data Index: 271229 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.2014. Min Act: -0.1700

Data Index: 1488224 (Python Code)

Max Activating Token Index: 647

Text #4

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1983. Min Act: -0.1700

Data Index: 1498944 (Python Code)

Max Activating Token Index: 329

Text #5

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1871. Min Act: -0.1700

Data Index: 299039 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1660. Min Act: -0.1700

Data Index: 1557771 (Python Code)

Max Activating Token Index: 399

Text #7

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1447. Min Act: -0.1700

Data Index: 1239882 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1540. Min Act: -0.1700

Data Index: 1558285 (Python Code)

Max Activating Token Index: 54

Text #9

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1572. Min Act: -0.1700

Data Index: 1441531 (Python Code)

Max Activating Token Index: 256

Text #10

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1492. Min Act: -0.1700

Data Index: 296187 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1446. Min Act: -0.1700

Data Index: 1513629 (Python Code)

Max Activating Token Index: 548

Text #12

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1411. Min Act: -0.1700

Data Index: 1396167 (Python Code)

Max Activating Token Index: 139

Text #13

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1422. Min Act: -0.1700

Data Index: 1446885 (Python Code)

Max Activating Token Index: 618

Text #14

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1317. Min Act: -0.1700

Data Index: 1527369 (Python Code)

Max Activating Token Index: 409

Text #15

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1148. Min Act: -0.1700

Data Index: 1014147 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1291. Min Act: -0.1700

Data Index: 816020 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1334. Min Act: -0.1700

Data Index: 1587646 (Python Code)

Max Activating Token Index: 440

Text #18

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1140. Min Act: -0.1700

Data Index: 725345 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 3.2716. Min Range: -3.2716

Max Act: 3.1295. Min Act: -0.1700

Data Index: 1296093 (C4 (Web Text))

Max Activating Token Index: 276