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

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

Neuron 956 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: 5.9743. Min Range: -5.9743

Max Act: 5.9743. Min Act: -0.1700

Data Index: 41538 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.9743. Min Act: -0.1700

Data Index: 22038 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.9743. Min Act: -0.1700

Data Index: 524066 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.9743. Min Act: -0.1700

Data Index: 872355 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.9743. Min Act: -0.1700

Data Index: 494473 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.9118. Min Act: -0.1700

Data Index: 1358913 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.8180. Min Act: -0.1700

Data Index: 241999 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.7868. Min Act: -0.1700

Data Index: 847443 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.7555. Min Act: -0.1700

Data Index: 524963 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.6461. Min Act: -0.1700

Data Index: 1109532 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.7711. Min Act: -0.1700

Data Index: 553412 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.6930. Min Act: -0.1700

Data Index: 899794 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.7243. Min Act: -0.1700

Data Index: 498718 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.7086. Min Act: -0.1700

Data Index: 1293313 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.6930. Min Act: -0.1700

Data Index: 375511 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.7243. Min Act: -0.1700

Data Index: 1063656 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.6149. Min Act: -0.1700

Data Index: 189312 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.5680. Min Act: -0.1700

Data Index: 448977 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.6149. Min Act: -0.1700

Data Index: 748027 (C4 (Web Text))

Max Activating Token Index: 911

Text #19

Max Range: 5.9743. Min Range: -5.9743

Max Act: 5.7243. Min Act: -0.1700

Data Index: 304288 (C4 (Web Text))

Max Activating Token Index: 224