Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 689 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.0177. Min Range: -5.0177

Max Act: 5.0177. Min Act: -0.1700

Data Index: 1179617 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 5.0177. Min Range: -5.0177

Max Act: 4.9084. Min Act: -0.1699

Data Index: 1435686 (Python Code)

Max Activating Token Index: 878

Text #2

Max Range: 5.0177. Min Range: -5.0177

Max Act: 4.8615. Min Act: -0.1700

Data Index: 1538472 (Python Code)

Max Activating Token Index: 538

Text #3

Max Range: 5.0177. Min Range: -5.0177

Max Act: 4.8302. Min Act: -0.1700

Data Index: 873929 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 5.0177. Min Range: -5.0177

Max Act: 4.7365. Min Act: -0.1700

Data Index: 1151649 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 5.0177. Min Range: -5.0177

Max Act: 4.6740. Min Act: -0.1700

Data Index: 355445 (C4 (Web Text))

Max Activating Token Index: 598

Text #6

Max Range: 5.0177. Min Range: -5.0177

Max Act: 4.6896. Min Act: -0.1700

Data Index: 1568922 (Python Code)

Max Activating Token Index: 544

Text #7

Max Range: 5.0177. Min Range: -5.0177

Max Act: 4.6271. Min Act: -0.1700

Data Index: 1651969 (Python Code)

Max Activating Token Index: 174

Text #8

Max Range: 5.0177. Min Range: -5.0177

Max Act: 4.5959. Min Act: -0.1700

Data Index: 1125533 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 5.0177. Min Range: -5.0177

Max Act: 4.6115. Min Act: -0.1700

Data Index: 1000395 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 5.0177. Min Range: -5.0177

Max Act: 4.5959. Min Act: -0.1700

Data Index: 1432179 (Python Code)

Max Activating Token Index: 186

Text #11

Max Range: 5.0177. Min Range: -5.0177

Max Act: 4.5646. Min Act: -0.1700

Data Index: 1514247 (Python Code)

Max Activating Token Index: 567

Text #12

Max Range: 5.0177. Min Range: -5.0177

Max Act: 4.5490. Min Act: -0.1579

Data Index: 1426679 (Python Code)

Max Activating Token Index: 875

Text #13

Max Range: 5.0177. Min Range: -5.0177

Max Act: 4.5959. Min Act: -0.1700

Data Index: 1583135 (Python Code)

Max Activating Token Index: 177

Text #14

Max Range: 5.0177. Min Range: -5.0177

Max Act: 4.5490. Min Act: -0.1700

Data Index: 918416 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 5.0177. Min Range: -5.0177

Max Act: 4.5802. Min Act: -0.1700

Data Index: 464281 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 5.0177. Min Range: -5.0177

Max Act: 4.5177. Min Act: -0.1700

Data Index: 1570806 (Python Code)

Max Activating Token Index: 437

Text #17

Max Range: 5.0177. Min Range: -5.0177

Max Act: 4.5334. Min Act: -0.1700

Data Index: 1646756 (Python Code)

Max Activating Token Index: 568

Text #18

Max Range: 5.0177. Min Range: -5.0177

Max Act: 4.5177. Min Act: -0.1700

Data Index: 110069 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 5.0177. Min Range: -5.0177

Max Act: 4.5334. Min Act: -0.1700

Data Index: 1362845 (Python Code)

Max Activating Token Index: 499