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

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

Neuron 793 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: 5.6147. Min Range: -5.6147

Max Act: 5.6147. Min Act: -0.1700

Data Index: 547143 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 5.6147. Min Range: -5.6147

Max Act: 5.3022. Min Act: -0.1700

Data Index: 639657 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 5.6147. Min Range: -5.6147

Max Act: 5.2709. Min Act: -0.1700

Data Index: 227495 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 5.6147. Min Range: -5.6147

Max Act: 5.3022. Min Act: -0.1700

Data Index: 801346 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 5.6147. Min Range: -5.6147

Max Act: 5.2397. Min Act: -0.1700

Data Index: 464698 (C4 (Web Text))

Max Activating Token Index: 332

Text #5

Max Range: 5.6147. Min Range: -5.6147

Max Act: 5.1459. Min Act: -0.1700

Data Index: 1271835 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 5.6147. Min Range: -5.6147

Max Act: 5.0522. Min Act: -0.1700

Data Index: 1061247 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 5.6147. Min Range: -5.6147

Max Act: 5.0834. Min Act: -0.1700

Data Index: 331954 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 5.6147. Min Range: -5.6147

Max Act: 5.0209. Min Act: -0.1700

Data Index: 789476 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 5.6147. Min Range: -5.6147

Max Act: 4.9897. Min Act: -0.1700

Data Index: 468847 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 5.6147. Min Range: -5.6147

Max Act: 5.0209. Min Act: -0.1700

Data Index: 234660 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 5.6147. Min Range: -5.6147

Max Act: 5.0522. Min Act: -0.1700

Data Index: 268417 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 5.6147. Min Range: -5.6147

Max Act: 5.0522. Min Act: -0.1700

Data Index: 504508 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 5.6147. Min Range: -5.6147

Max Act: 4.9897. Min Act: -0.1695

Data Index: 774036 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 5.6147. Min Range: -5.6147

Max Act: 4.9897. Min Act: -0.1700

Data Index: 915197 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 5.6147. Min Range: -5.6147

Max Act: 4.9897. Min Act: -0.1699

Data Index: 350693 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 5.6147. Min Range: -5.6147

Max Act: 4.9897. Min Act: -0.1700

Data Index: 971360 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 5.6147. Min Range: -5.6147

Max Act: 4.9584. Min Act: -0.1700

Data Index: 337468 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 5.6147. Min Range: -5.6147

Max Act: 4.9272. Min Act: -0.1698

Data Index: 896729 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 5.6147. Min Range: -5.6147

Max Act: 4.9272. Min Act: -0.1700

Data Index: 618109 (C4 (Web Text))

Max Activating Token Index: 53