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

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

Neuron 218 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: 3.3868. Min Range: -3.3868

Max Act: 3.3868. Min Act: -0.1654

Data Index: 872501 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 3.3868. Min Range: -3.3868

Max Act: 3.3497. Min Act: -0.1694

Data Index: 62376 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 3.3868. Min Range: -3.3868

Max Act: 3.3643. Min Act: -0.1697

Data Index: 319637 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 3.3868. Min Range: -3.3868

Max Act: 3.3489. Min Act: -0.1700

Data Index: 1077806 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 3.3868. Min Range: -3.3868

Max Act: 3.3295. Min Act: -0.1635

Data Index: 123558 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 3.3868. Min Range: -3.3868

Max Act: 3.3245. Min Act: -0.1700

Data Index: 164001 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 3.3868. Min Range: -3.3868

Max Act: 3.3256. Min Act: -0.1700

Data Index: 1012801 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 3.3868. Min Range: -3.3868

Max Act: 3.2676. Min Act: -0.1695

Data Index: 177079 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 3.3868. Min Range: -3.3868

Max Act: 3.2804. Min Act: -0.1700

Data Index: 820092 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 3.3868. Min Range: -3.3868

Max Act: 3.2821. Min Act: -0.1700

Data Index: 1031351 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 3.3868. Min Range: -3.3868

Max Act: 3.2822. Min Act: -0.1698

Data Index: 1130488 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 3.3868. Min Range: -3.3868

Max Act: 3.2460. Min Act: -0.1699

Data Index: 332192 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 3.3868. Min Range: -3.3868

Max Act: 3.2579. Min Act: -0.1700

Data Index: 36581 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 3.3868. Min Range: -3.3868

Max Act: 3.2523. Min Act: -0.1699

Data Index: 407902 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 3.3868. Min Range: -3.3868

Max Act: 3.2389. Min Act: -0.1699

Data Index: 994004 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 3.3868. Min Range: -3.3868

Max Act: 3.2399. Min Act: -0.1700

Data Index: 541996 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 3.3868. Min Range: -3.3868

Max Act: 3.2269. Min Act: -0.1698

Data Index: 1091184 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 3.3868. Min Range: -3.3868

Max Act: 3.2289. Min Act: -0.1698

Data Index: 410047 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 3.3868. Min Range: -3.3868

Max Act: 3.2259. Min Act: -0.1700

Data Index: 754674 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 3.3868. Min Range: -3.3868

Max Act: 3.2228. Min Act: -0.1622

Data Index: 1014332 (C4 (Web Text))

Max Activating Token Index: 868