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

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

Neuron 110 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: 3.0202. Min Range: -3.0202

Max Act: 3.0202. Min Act: -0.1700

Data Index: 1001877 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 3.0202. Min Range: -3.0202

Max Act: 3.0202. Min Act: -0.1700

Data Index: 598178 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 3.0202. Min Range: -3.0202

Max Act: 2.9727. Min Act: -0.1700

Data Index: 1215978 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 3.0202. Min Range: -3.0202

Max Act: 2.9727. Min Act: -0.1700

Data Index: 127711 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 3.0202. Min Range: -3.0202

Max Act: 2.9411. Min Act: -0.1700

Data Index: 1202605 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 3.0202. Min Range: -3.0202

Max Act: 2.9252. Min Act: -0.1700

Data Index: 952186 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 3.0202. Min Range: -3.0202

Max Act: 2.9094. Min Act: -0.1700

Data Index: 497644 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 3.0202. Min Range: -3.0202

Max Act: 2.9094. Min Act: -0.1700

Data Index: 421433 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 3.0202. Min Range: -3.0202

Max Act: 2.8776. Min Act: -0.1700

Data Index: 1265485 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 3.0202. Min Range: -3.0202

Max Act: 2.8618. Min Act: -0.1700

Data Index: 573067 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 3.0202. Min Range: -3.0202

Max Act: 2.8300. Min Act: -0.1700

Data Index: 61824 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 3.0202. Min Range: -3.0202

Max Act: 2.7822. Min Act: -0.1700

Data Index: 593874 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 3.0202. Min Range: -3.0202

Max Act: 2.6061. Min Act: -0.1700

Data Index: 1029984 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 3.0202. Min Range: -3.0202

Max Act: 2.5416. Min Act: -0.1700

Data Index: 1268305 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 3.0202. Min Range: -3.0202

Max Act: 2.5416. Min Act: -0.1700

Data Index: 14851 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 3.0202. Min Range: -3.0202

Max Act: 2.4931. Min Act: -0.1700

Data Index: 269145 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 3.0202. Min Range: -3.0202

Max Act: 2.4931. Min Act: -0.1700

Data Index: 1331302 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 3.0202. Min Range: -3.0202

Max Act: 2.4769. Min Act: -0.1700

Data Index: 1463652 (Python Code)

Max Activating Token Index: 158

Text #18

Max Range: 3.0202. Min Range: -3.0202

Max Act: 2.4607. Min Act: -0.1700

Data Index: 275221 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 3.0202. Min Range: -3.0202

Max Act: 2.4769. Min Act: -0.1700

Data Index: 952871 (C4 (Web Text))

Max Activating Token Index: 723