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

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

Neuron 404 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.5439. Min Act: -0.1700

Data Index: 803511 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.4186. Min Act: -0.1700

Data Index: 1214187 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.4813. Min Act: -0.1700

Data Index: 1232503 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.4186. Min Act: -0.1700

Data Index: 452967 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.4186. Min Act: -0.1700

Data Index: 296615 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.4186. Min Act: -0.1700

Data Index: 337901 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.3558. Min Act: -0.1700

Data Index: 773678 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.4186. Min Act: -0.1700

Data Index: 233762 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.4186. Min Act: -0.1700

Data Index: 230695 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.3872. Min Act: -0.1700

Data Index: 345337 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.3872. Min Act: -0.1700

Data Index: 667566 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.3872. Min Act: -0.1700

Data Index: 761618 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.2930. Min Act: -0.1700

Data Index: 171243 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.3558. Min Act: -0.1700

Data Index: 846710 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.3872. Min Act: -0.1700

Data Index: 8722 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.3244. Min Act: -0.1700

Data Index: 124475 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.3244. Min Act: -0.1700

Data Index: 142674 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.3244. Min Act: -0.1700

Data Index: 1018084 (C4 (Web Text))

Max Activating Token Index: 296

Text #18

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.3244. Min Act: -0.1700

Data Index: 1068009 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 3.5439. Min Range: -3.5439

Max Act: 3.3558. Min Act: -0.1700

Data Index: 750189 (C4 (Web Text))

Max Activating Token Index: 33