Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1134 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.2628. Min Range: -5.2628

Max Act: 5.2628. Min Act: -0.1700

Data Index: 1012580 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 5.2628. Min Range: -5.2628

Max Act: 5.2003. Min Act: -0.1700

Data Index: 373334 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 5.2628. Min Range: -5.2628

Max Act: 5.0128. Min Act: -0.1700

Data Index: 343456 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 5.2628. Min Range: -5.2628

Max Act: 4.9503. Min Act: -0.1700

Data Index: 380194 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 5.2628. Min Range: -5.2628

Max Act: 4.9190. Min Act: -0.1700

Data Index: 814392 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 5.2628. Min Range: -5.2628

Max Act: 4.9815. Min Act: -0.1700

Data Index: 897265 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 5.2628. Min Range: -5.2628

Max Act: 4.9190. Min Act: -0.1700

Data Index: 1356470 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 5.2628. Min Range: -5.2628

Max Act: 4.8878. Min Act: -0.1700

Data Index: 1145199 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 5.2628. Min Range: -5.2628

Max Act: 4.8565. Min Act: -0.1700

Data Index: 1333352 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 5.2628. Min Range: -5.2628

Max Act: 4.8565. Min Act: -0.1700

Data Index: 876062 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 5.2628. Min Range: -5.2628

Max Act: 4.8878. Min Act: -0.1700

Data Index: 928354 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 5.2628. Min Range: -5.2628

Max Act: 4.9190. Min Act: -0.1700

Data Index: 264365 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 5.2628. Min Range: -5.2628

Max Act: 4.8253. Min Act: -0.1700

Data Index: 1050558 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 5.2628. Min Range: -5.2628

Max Act: 4.8565. Min Act: -0.1700

Data Index: 463816 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 5.2628. Min Range: -5.2628

Max Act: 4.8253. Min Act: -0.1700

Data Index: 120751 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 5.2628. Min Range: -5.2628

Max Act: 4.7628. Min Act: -0.1700

Data Index: 1020651 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 5.2628. Min Range: -5.2628

Max Act: 4.8253. Min Act: -0.1700

Data Index: 856262 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 5.2628. Min Range: -5.2628

Max Act: 4.7315. Min Act: -0.1700

Data Index: 1014122 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 5.2628. Min Range: -5.2628

Max Act: 4.7003. Min Act: -0.1700

Data Index: 801568 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 5.2628. Min Range: -5.2628

Max Act: 4.7003. Min Act: -0.1700

Data Index: 604956 (C4 (Web Text))

Max Activating Token Index: 159