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

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

Neuron 479 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.5779. Min Act: -0.1700

Data Index: 15919 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.5779. Min Act: -0.1700

Data Index: 147365 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.4842. Min Act: -0.1700

Data Index: 1305341 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.5467. Min Act: -0.1700

Data Index: 931423 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.4842. Min Act: -0.1700

Data Index: 1293253 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.5154. Min Act: -0.1700

Data Index: 504476 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.4529. Min Act: -0.1700

Data Index: 426014 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.4842. Min Act: -0.1700

Data Index: 173454 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.5154. Min Act: -0.1700

Data Index: 1224519 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.5154. Min Act: -0.1700

Data Index: 756147 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.5154. Min Act: -0.1700

Data Index: 1120478 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.4529. Min Act: -0.1700

Data Index: 24911 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.4529. Min Act: -0.1700

Data Index: 1063354 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.4529. Min Act: -0.1700

Data Index: 335789 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.4529. Min Act: -0.1699

Data Index: 1016526 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.4529. Min Act: -0.1700

Data Index: 944268 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.4529. Min Act: -0.1700

Data Index: 253209 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.4529. Min Act: -0.1700

Data Index: 1022722 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.4217. Min Act: -0.1700

Data Index: 271530 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 5.5779. Min Range: -5.5779

Max Act: 5.4529. Min Act: -0.1700

Data Index: 503877 (C4 (Web Text))

Max Activating Token Index: 194