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

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

Neuron 80 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4388. Min Range: -7.4388

Max Act: 7.4388. Min Act: -0.0000

Data Index: 373896 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 7.4388. Min Range: -7.4388

Max Act: 7.3763. Min Act: -0.1150

Data Index: 273394 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 7.4388. Min Range: -7.4388

Max Act: 7.3763. Min Act: -0.1080

Data Index: 766730 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 7.4388. Min Range: -7.4388

Max Act: 7.3450. Min Act: -0.1320

Data Index: 524660 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 7.4388. Min Range: -7.4388

Max Act: 7.3138. Min Act: -0.1583

Data Index: 1251810 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 7.4388. Min Range: -7.4388

Max Act: 7.2200. Min Act: -0.1700

Data Index: 38510 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 7.4388. Min Range: -7.4388

Max Act: 6.7825. Min Act: -0.1697

Data Index: 138536 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 7.4388. Min Range: -7.4388

Max Act: 6.6888. Min Act: -0.1700

Data Index: 1339434 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 7.4388. Min Range: -7.4388

Max Act: 6.6888. Min Act: -0.1700

Data Index: 115342 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 7.4388. Min Range: -7.4388

Max Act: 6.5950. Min Act: -0.1688

Data Index: 1144189 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 7.4388. Min Range: -7.4388

Max Act: 6.5950. Min Act: -0.1699

Data Index: 1173895 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 7.4388. Min Range: -7.4388

Max Act: 6.5638. Min Act: -0.1700

Data Index: 334496 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 7.4388. Min Range: -7.4388

Max Act: 6.5325. Min Act: -0.1700

Data Index: 861093 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 7.4388. Min Range: -7.4388

Max Act: 6.5325. Min Act: -0.1700

Data Index: 689134 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 7.4388. Min Range: -7.4388

Max Act: 6.4700. Min Act: -0.1379

Data Index: 55418 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 7.4388. Min Range: -7.4388

Max Act: 6.5013. Min Act: -0.1285

Data Index: 854667 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 7.4388. Min Range: -7.4388

Max Act: 6.5013. Min Act: -0.0000

Data Index: 860919 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 7.4388. Min Range: -7.4388

Max Act: 6.4700. Min Act: -0.1700

Data Index: 591358 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 7.4388. Min Range: -7.4388

Max Act: 6.4700. Min Act: -0.1650

Data Index: 244706 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 7.4388. Min Range: -7.4388

Max Act: 6.4075. Min Act: -0.1700

Data Index: 573150 (C4 (Web Text))

Max Activating Token Index: 974