Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1438 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.8205. Min Act: -0.1700

Data Index: 483610 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.8205. Min Act: -0.1700

Data Index: 1218291 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.7892. Min Act: -0.1700

Data Index: 486264 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.7579. Min Act: -0.1700

Data Index: 909150 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.7423. Min Act: -0.1700

Data Index: 205506 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.7735. Min Act: -0.1700

Data Index: 498812 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.7266. Min Act: -0.1700

Data Index: 25893 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.7579. Min Act: -0.1700

Data Index: 584965 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.7266. Min Act: -0.1700

Data Index: 696783 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.7266. Min Act: -0.1700

Data Index: 755118 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.7579. Min Act: -0.1700

Data Index: 1134069 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.7423. Min Act: -0.1700

Data Index: 120061 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.7266. Min Act: -0.1700

Data Index: 900607 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.7110. Min Act: -0.1700

Data Index: 641218 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.6953. Min Act: -0.1700

Data Index: 264504 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.6797. Min Act: -0.1700

Data Index: 273122 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.6953. Min Act: -0.1700

Data Index: 1178921 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.6953. Min Act: -0.1700

Data Index: 1326614 (C4 (Web Text))

Max Activating Token Index: 511

Text #18

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.6797. Min Act: -0.1700

Data Index: 440503 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 3.8205. Min Range: -3.8205

Max Act: 3.6953. Min Act: -0.1700

Data Index: 1126001 (C4 (Web Text))

Max Activating Token Index: 969