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

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

Neuron 1417 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.9568. Min Act: -0.1700

Data Index: 21782 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.7848. Min Act: -0.1700

Data Index: 377487 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.7222. Min Act: -0.1700

Data Index: 1294317 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.6909. Min Act: -0.1700

Data Index: 1214317 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.6753. Min Act: -0.1700

Data Index: 866439 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.6753. Min Act: -0.1700

Data Index: 423262 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.6753. Min Act: -0.1700

Data Index: 759141 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.6597. Min Act: -0.1700

Data Index: 400219 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.5970. Min Act: -0.1700

Data Index: 166159 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.6127. Min Act: -0.1700

Data Index: 336738 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.5970. Min Act: -0.1700

Data Index: 769429 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.5501. Min Act: -0.1700

Data Index: 698219 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.5814. Min Act: -0.1700

Data Index: 640224 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.5657. Min Act: -0.1700

Data Index: 514169 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.5344. Min Act: -0.1700

Data Index: 108885 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.5344. Min Act: -0.1700

Data Index: 626906 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.5344. Min Act: -0.1700

Data Index: 349971 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.5031. Min Act: -0.1700

Data Index: 996731 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.4874. Min Act: -0.1700

Data Index: 379387 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 3.9568. Min Range: -3.9568

Max Act: 3.5031. Min Act: -0.1700

Data Index: 1135002 (C4 (Web Text))

Max Activating Token Index: 857