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

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

Neuron 1378 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: 3.3620. Min Range: -3.3620

Max Act: 3.3620. Min Act: -0.1698

Data Index: 222272 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 3.3620. Min Range: -3.3620

Max Act: 3.3041. Min Act: -0.1567

Data Index: 782540 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 3.3620. Min Range: -3.3620

Max Act: 3.3116. Min Act: -0.1627

Data Index: 280440 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 3.3620. Min Range: -3.3620

Max Act: 3.3043. Min Act: -0.1698

Data Index: 1520527 (Python Code)

Max Activating Token Index: 156

Text #4

Max Range: 3.3620. Min Range: -3.3620

Max Act: 3.2912. Min Act: -0.1696

Data Index: 309056 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 3.3620. Min Range: -3.3620

Max Act: 3.2706. Min Act: -0.1700

Data Index: 15048 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 3.3620. Min Range: -3.3620

Max Act: 3.2609. Min Act: -0.1542

Data Index: 808488 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 3.3620. Min Range: -3.3620

Max Act: 3.2568. Min Act: -0.1700

Data Index: 113616 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 3.3620. Min Range: -3.3620

Max Act: 3.2527. Min Act: -0.1636

Data Index: 507953 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 3.3620. Min Range: -3.3620

Max Act: 3.2169. Min Act: -0.1696

Data Index: 1349783 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 3.3620. Min Range: -3.3620

Max Act: 3.2263. Min Act: -0.1633

Data Index: 203674 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 3.3620. Min Range: -3.3620

Max Act: 3.2371. Min Act: -0.1700

Data Index: 249309 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 3.3620. Min Range: -3.3620

Max Act: 3.2489. Min Act: -0.1700

Data Index: 1205289 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 3.3620. Min Range: -3.3620

Max Act: 3.2309. Min Act: -0.1699

Data Index: 633744 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 3.3620. Min Range: -3.3620

Max Act: 3.2340. Min Act: -0.1689

Data Index: 1148554 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 3.3620. Min Range: -3.3620

Max Act: 3.2278. Min Act: -0.1529

Data Index: 872688 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 3.3620. Min Range: -3.3620

Max Act: 3.2001. Min Act: -0.1687

Data Index: 663495 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 3.3620. Min Range: -3.3620

Max Act: 3.1888. Min Act: -0.1700

Data Index: 1284554 (C4 (Web Text))

Max Activating Token Index: 103

Text #18

Max Range: 3.3620. Min Range: -3.3620

Max Act: 3.2014. Min Act: -0.1698

Data Index: 89106 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 3.3620. Min Range: -3.3620

Max Act: 3.1750. Min Act: -0.1646

Data Index: 392115 (C4 (Web Text))

Max Activating Token Index: 982