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

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

Neuron 565 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: 5.8999. Min Range: -5.8999

Max Act: 5.8999. Min Act: -0.1699

Data Index: 563633 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 5.8999. Min Range: -5.8999

Max Act: 5.8687. Min Act: -0.1700

Data Index: 227785 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 5.8999. Min Range: -5.8999

Max Act: 5.8999. Min Act: -0.1699

Data Index: 1262881 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 5.8999. Min Range: -5.8999

Max Act: 5.8687. Min Act: -0.1700

Data Index: 1168947 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 5.8999. Min Range: -5.8999

Max Act: 5.8374. Min Act: -0.1700

Data Index: 477681 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 5.8999. Min Range: -5.8999

Max Act: 5.8374. Min Act: -0.1700

Data Index: 428318 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 5.8999. Min Range: -5.8999

Max Act: 5.8374. Min Act: -0.1700

Data Index: 260950 (C4 (Web Text))

Max Activating Token Index: 273

Text #7

Max Range: 5.8999. Min Range: -5.8999

Max Act: 5.8374. Min Act: -0.1699

Data Index: 951906 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 5.8999. Min Range: -5.8999

Max Act: 5.8374. Min Act: -0.1700

Data Index: 683277 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 5.8999. Min Range: -5.8999

Max Act: 5.7437. Min Act: -0.1700

Data Index: 635149 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 5.8999. Min Range: -5.8999

Max Act: 5.7437. Min Act: -0.1700

Data Index: 690876 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 5.8999. Min Range: -5.8999

Max Act: 5.7749. Min Act: -0.1700

Data Index: 914424 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 5.8999. Min Range: -5.8999

Max Act: 5.7749. Min Act: -0.1700

Data Index: 1229028 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 5.8999. Min Range: -5.8999

Max Act: 5.7124. Min Act: -0.1699

Data Index: 803658 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 5.8999. Min Range: -5.8999

Max Act: 5.7437. Min Act: -0.1699

Data Index: 1121671 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 5.8999. Min Range: -5.8999

Max Act: 5.7437. Min Act: -0.1700

Data Index: 742610 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 5.8999. Min Range: -5.8999

Max Act: 5.7124. Min Act: -0.1700

Data Index: 283014 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 5.8999. Min Range: -5.8999

Max Act: 5.7124. Min Act: -0.1699

Data Index: 370100 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 5.8999. Min Range: -5.8999

Max Act: 5.6187. Min Act: -0.1700

Data Index: 307281 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 5.8999. Min Range: -5.8999

Max Act: 5.6187. Min Act: -0.1699

Data Index: 586368 (C4 (Web Text))

Max Activating Token Index: 765