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

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

Neuron 1498 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: 3.7022. Min Range: -3.7022

Max Act: 3.7022. Min Act: -0.1700

Data Index: 167792 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 3.7022. Min Range: -3.7022

Max Act: 3.6709. Min Act: -0.1700

Data Index: 197527 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 3.7022. Min Range: -3.7022

Max Act: 3.5770. Min Act: -0.1700

Data Index: 138656 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 3.7022. Min Range: -3.7022

Max Act: 3.5770. Min Act: -0.1700

Data Index: 503558 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 3.7022. Min Range: -3.7022

Max Act: 3.5457. Min Act: -0.1700

Data Index: 324049 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 3.7022. Min Range: -3.7022

Max Act: 3.5143. Min Act: -0.1700

Data Index: 917223 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 3.7022. Min Range: -3.7022

Max Act: 3.5143. Min Act: -0.1700

Data Index: 442498 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 3.7022. Min Range: -3.7022

Max Act: 3.3575. Min Act: -0.1700

Data Index: 632112 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 3.7022. Min Range: -3.7022

Max Act: 3.4830. Min Act: -0.1700

Data Index: 639014 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 3.7022. Min Range: -3.7022

Max Act: 3.4673. Min Act: -0.1700

Data Index: 1293849 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 3.7022. Min Range: -3.7022

Max Act: 3.4516. Min Act: -0.1700

Data Index: 212338 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 3.7022. Min Range: -3.7022

Max Act: 3.4203. Min Act: -0.1700

Data Index: 1097468 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 3.7022. Min Range: -3.7022

Max Act: 3.4360. Min Act: -0.1700

Data Index: 1302496 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 3.7022. Min Range: -3.7022

Max Act: 3.4673. Min Act: -0.1700

Data Index: 640414 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 3.7022. Min Range: -3.7022

Max Act: 3.4673. Min Act: -0.1700

Data Index: 844186 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 3.7022. Min Range: -3.7022

Max Act: 3.4203. Min Act: -0.1700

Data Index: 1196638 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 3.7022. Min Range: -3.7022

Max Act: 3.4046. Min Act: -0.1700

Data Index: 755258 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 3.7022. Min Range: -3.7022

Max Act: 3.3418. Min Act: -0.1700

Data Index: 253895 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 3.7022. Min Range: -3.7022

Max Act: 3.4203. Min Act: -0.1700

Data Index: 1191721 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 3.7022. Min Range: -3.7022

Max Act: 3.4046. Min Act: -0.1700

Data Index: 1343077 (C4 (Web Text))

Max Activating Token Index: 617