Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1218 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.1426. Min Range: -5.1426

Max Act: 5.0801. Min Act: -0.1700

Data Index: 1203493 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 5.1426. Min Range: -5.1426

Max Act: 5.1426. Min Act: -0.1700

Data Index: 1173583 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 5.1426. Min Range: -5.1426

Max Act: 5.0176. Min Act: -0.1700

Data Index: 918883 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 5.1426. Min Range: -5.1426

Max Act: 4.9863. Min Act: -0.1700

Data Index: 739829 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 5.1426. Min Range: -5.1426

Max Act: 4.9551. Min Act: -0.1700

Data Index: 758752 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 5.1426. Min Range: -5.1426

Max Act: 4.9238. Min Act: -0.1700

Data Index: 301024 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 5.1426. Min Range: -5.1426

Max Act: 4.9551. Min Act: -0.1700

Data Index: 299754 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 5.1426. Min Range: -5.1426

Max Act: 4.9238. Min Act: -0.1700

Data Index: 150691 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 5.1426. Min Range: -5.1426

Max Act: 4.8926. Min Act: -0.1700

Data Index: 687913 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 5.1426. Min Range: -5.1426

Max Act: 4.8613. Min Act: -0.1700

Data Index: 469476 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 5.1426. Min Range: -5.1426

Max Act: 4.8613. Min Act: -0.1700

Data Index: 888760 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 5.1426. Min Range: -5.1426

Max Act: 4.8926. Min Act: -0.1700

Data Index: 509726 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 5.1426. Min Range: -5.1426

Max Act: 4.7363. Min Act: -0.1700

Data Index: 1144894 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 5.1426. Min Range: -5.1426

Max Act: 4.8613. Min Act: -0.1700

Data Index: 266935 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 5.1426. Min Range: -5.1426

Max Act: 4.8301. Min Act: -0.1700

Data Index: 222833 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 5.1426. Min Range: -5.1426

Max Act: 4.7988. Min Act: -0.1700

Data Index: 1021478 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 5.1426. Min Range: -5.1426

Max Act: 4.7988. Min Act: -0.1700

Data Index: 65745 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 5.1426. Min Range: -5.1426

Max Act: 4.8613. Min Act: -0.1700

Data Index: 235980 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 5.1426. Min Range: -5.1426

Max Act: 4.7988. Min Act: -0.1700

Data Index: 68516 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 5.1426. Min Range: -5.1426

Max Act: 4.8301. Min Act: -0.1700

Data Index: 643916 (C4 (Web Text))

Max Activating Token Index: 699