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

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

Neuron 1837 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0317. Min Range: -3.0317

Max Act: 3.0317. Min Act: -0.1700

Data Index: 1304044 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 3.0317. Min Range: -3.0317

Max Act: 3.0317. Min Act: -0.1700

Data Index: 510725 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.9842. Min Act: -0.1700

Data Index: 1119172 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.9684. Min Act: -0.1700

Data Index: 1136636 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.9526. Min Act: -0.1700

Data Index: 1654712 (Python Code)

Max Activating Token Index: 194

Text #5

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.9368. Min Act: -0.1700

Data Index: 1337853 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.9526. Min Act: -0.1700

Data Index: 664327 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.9368. Min Act: -0.1700

Data Index: 969277 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.9209. Min Act: -0.1700

Data Index: 668183 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.9209. Min Act: -0.1700

Data Index: 1119739 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.9209. Min Act: -0.1700

Data Index: 474528 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.8892. Min Act: -0.1700

Data Index: 681253 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.9051. Min Act: -0.1700

Data Index: 1263844 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.9051. Min Act: -0.1700

Data Index: 217698 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.9051. Min Act: -0.1700

Data Index: 804556 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.8892. Min Act: -0.1700

Data Index: 1174033 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.8892. Min Act: -0.1700

Data Index: 869676 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.9051. Min Act: -0.1700

Data Index: 593718 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.8892. Min Act: -0.1700

Data Index: 158321 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 3.0317. Min Range: -3.0317

Max Act: 2.9051. Min Act: -0.1700

Data Index: 882622 (C4 (Web Text))

Max Activating Token Index: 26