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

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

Neuron 1330 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: 3.3128. Min Range: -3.3128

Max Act: 3.3128. Min Act: -0.1700

Data Index: 534172 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 3.3128. Min Range: -3.3128

Max Act: 3.2947. Min Act: -0.1700

Data Index: 773473 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 3.3128. Min Range: -3.3128

Max Act: 3.2332. Min Act: -0.1608

Data Index: 97123 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 3.3128. Min Range: -3.3128

Max Act: 3.2416. Min Act: -0.1695

Data Index: 420591 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 3.3128. Min Range: -3.3128

Max Act: 3.2200. Min Act: -0.1699

Data Index: 29928 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 3.3128. Min Range: -3.3128

Max Act: 3.1767. Min Act: -0.1700

Data Index: 184437 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 3.3128. Min Range: -3.3128

Max Act: 3.1889. Min Act: -0.1700

Data Index: 880657 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 3.3128. Min Range: -3.3128

Max Act: 3.1912. Min Act: -0.1700

Data Index: 168201 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 3.3128. Min Range: -3.3128

Max Act: 3.1883. Min Act: -0.1700

Data Index: 635187 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 3.3128. Min Range: -3.3128

Max Act: 3.1717. Min Act: -0.1700

Data Index: 1094493 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 3.3128. Min Range: -3.3128

Max Act: 3.1741. Min Act: -0.1700

Data Index: 1173050 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 3.3128. Min Range: -3.3128

Max Act: 3.1502. Min Act: -0.1700

Data Index: 916685 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 3.3128. Min Range: -3.3128

Max Act: 3.1511. Min Act: -0.1288

Data Index: 134427 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 3.3128. Min Range: -3.3128

Max Act: 3.1446. Min Act: -0.1699

Data Index: 518437 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 3.3128. Min Range: -3.3128

Max Act: 3.1541. Min Act: -0.1700

Data Index: 186902 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 3.3128. Min Range: -3.3128

Max Act: 3.1553. Min Act: -0.1700

Data Index: 1330935 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 3.3128. Min Range: -3.3128

Max Act: 3.1510. Min Act: -0.1700

Data Index: 35198 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 3.3128. Min Range: -3.3128

Max Act: 3.1319. Min Act: -0.1700

Data Index: 225373 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 3.3128. Min Range: -3.3128

Max Act: 3.1518. Min Act: -0.1700

Data Index: 878803 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 3.3128. Min Range: -3.3128

Max Act: 3.1241. Min Act: -0.1700

Data Index: 332018 (C4 (Web Text))

Max Activating Token Index: 118