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

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

Neuron 1102 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: 5.2182. Min Range: -5.2182

Max Act: 5.2182. Min Act: -0.1700

Data Index: 554457 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 5.2182. Min Range: -5.2182

Max Act: 5.1869. Min Act: -0.1692

Data Index: 1113358 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 5.2182. Min Range: -5.2182

Max Act: 5.2182. Min Act: -0.1700

Data Index: 160602 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 5.2182. Min Range: -5.2182

Max Act: 5.1869. Min Act: -0.1700

Data Index: 753715 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 5.2182. Min Range: -5.2182

Max Act: 5.1869. Min Act: -0.1700

Data Index: 321992 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 5.2182. Min Range: -5.2182

Max Act: 5.1244. Min Act: -0.1700

Data Index: 260474 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 5.2182. Min Range: -5.2182

Max Act: 5.1244. Min Act: -0.1700

Data Index: 1260954 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 5.2182. Min Range: -5.2182

Max Act: 5.0619. Min Act: -0.1700

Data Index: 788686 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 5.2182. Min Range: -5.2182

Max Act: 5.0619. Min Act: -0.1700

Data Index: 628 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 5.2182. Min Range: -5.2182

Max Act: 4.9994. Min Act: -0.1700

Data Index: 159116 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 5.2182. Min Range: -5.2182

Max Act: 4.9994. Min Act: -0.1700

Data Index: 514412 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 5.2182. Min Range: -5.2182

Max Act: 5.0307. Min Act: -0.1700

Data Index: 97136 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 5.2182. Min Range: -5.2182

Max Act: 5.0307. Min Act: -0.1699

Data Index: 1176921 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 5.2182. Min Range: -5.2182

Max Act: 4.9994. Min Act: -0.1700

Data Index: 1272996 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 5.2182. Min Range: -5.2182

Max Act: 4.9994. Min Act: -0.1699

Data Index: 1331532 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 5.2182. Min Range: -5.2182

Max Act: 4.9682. Min Act: -0.1700

Data Index: 553385 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 5.2182. Min Range: -5.2182

Max Act: 4.9994. Min Act: -0.1700

Data Index: 97227 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 5.2182. Min Range: -5.2182

Max Act: 4.9994. Min Act: -0.1700

Data Index: 513853 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 5.2182. Min Range: -5.2182

Max Act: 4.9369. Min Act: -0.1700

Data Index: 346355 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 5.2182. Min Range: -5.2182

Max Act: 4.9369. Min Act: -0.1700

Data Index: 40840 (C4 (Web Text))

Max Activating Token Index: 250