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

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

Neuron 1009 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: 7.0846. Min Range: -7.0846

Max Act: 7.0846. Min Act: -0.1700

Data Index: 258326 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.9908. Min Act: -0.1700

Data Index: 270397 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.8346. Min Act: -0.1700

Data Index: 1034292 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.7408. Min Act: -0.1700

Data Index: 16381 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.8033. Min Act: -0.1700

Data Index: 482776 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.7408. Min Act: -0.1700

Data Index: 240004 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.6158. Min Act: -0.1700

Data Index: 1253391 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.5221. Min Act: -0.1700

Data Index: 135898 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.5221. Min Act: -0.1700

Data Index: 30918 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.5221. Min Act: -0.1700

Data Index: 1060307 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.5533. Min Act: -0.1700

Data Index: 891377 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.5221. Min Act: -0.1700

Data Index: 946170 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.4908. Min Act: -0.1694

Data Index: 556596 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.3971. Min Act: -0.1700

Data Index: 266257 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.4283. Min Act: -0.1700

Data Index: 1275477 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.4596. Min Act: -0.1700

Data Index: 977641 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.4283. Min Act: -0.1700

Data Index: 248793 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.3658. Min Act: -0.1700

Data Index: 1057309 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.3658. Min Act: -0.1700

Data Index: 1163375 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 7.0846. Min Range: -7.0846

Max Act: 6.3346. Min Act: -0.1700

Data Index: 856356 (C4 (Web Text))

Max Activating Token Index: 358