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

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

Neuron 529 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: 5.7215. Min Range: -5.7215

Max Act: 5.7215. Min Act: -0.1700

Data Index: 1358558 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 5.7215. Min Range: -5.7215

Max Act: 5.4090. Min Act: -0.1699

Data Index: 1020016 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 5.7215. Min Range: -5.7215

Max Act: 5.3465. Min Act: -0.1700

Data Index: 488971 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 5.7215. Min Range: -5.7215

Max Act: 5.1902. Min Act: -0.1700

Data Index: 467365 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 5.7215. Min Range: -5.7215

Max Act: 5.1902. Min Act: -0.1700

Data Index: 996452 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 5.7215. Min Range: -5.7215

Max Act: 5.2527. Min Act: -0.1700

Data Index: 1003672 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 5.7215. Min Range: -5.7215

Max Act: 5.1590. Min Act: -0.1699

Data Index: 996955 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 5.7215. Min Range: -5.7215

Max Act: 5.1277. Min Act: -0.1700

Data Index: 1390169 (Python Code)

Max Activating Token Index: 954

Text #8

Max Range: 5.7215. Min Range: -5.7215

Max Act: 5.0965. Min Act: -0.1699

Data Index: 943697 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 5.7215. Min Range: -5.7215

Max Act: 5.0652. Min Act: -0.1700

Data Index: 458987 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 5.7215. Min Range: -5.7215

Max Act: 5.1277. Min Act: -0.1700

Data Index: 258858 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 5.7215. Min Range: -5.7215

Max Act: 5.0027. Min Act: -0.1699

Data Index: 279964 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 5.7215. Min Range: -5.7215

Max Act: 5.0965. Min Act: -0.1700

Data Index: 696118 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 5.7215. Min Range: -5.7215

Max Act: 5.0340. Min Act: -0.1700

Data Index: 1322424 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 5.7215. Min Range: -5.7215

Max Act: 5.0340. Min Act: -0.1700

Data Index: 53438 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 5.7215. Min Range: -5.7215

Max Act: 5.0652. Min Act: -0.1700

Data Index: 273999 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 5.7215. Min Range: -5.7215

Max Act: 5.0340. Min Act: -0.1700

Data Index: 777445 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 5.7215. Min Range: -5.7215

Max Act: 4.9402. Min Act: -0.1700

Data Index: 6545 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 5.7215. Min Range: -5.7215

Max Act: 4.9402. Min Act: -0.1700

Data Index: 1194261 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 5.7215. Min Range: -5.7215

Max Act: 4.9715. Min Act: -0.1700

Data Index: 493075 (C4 (Web Text))

Max Activating Token Index: 459