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

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

Neuron 1764 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.7749. Min Act: -0.1700

Data Index: 1092383 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.5874. Min Act: -0.1700

Data Index: 973925 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.5874. Min Act: -0.1700

Data Index: 878088 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.5249. Min Act: -0.1700

Data Index: 79897 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.4936. Min Act: -0.1700

Data Index: 1268933 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.4311. Min Act: -0.1700

Data Index: 1053045 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.4936. Min Act: -0.1700

Data Index: 456196 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.3374. Min Act: -0.1700

Data Index: 1251140 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.3686. Min Act: -0.1700

Data Index: 441633 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.4311. Min Act: -0.1700

Data Index: 360791 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.3999. Min Act: -0.1700

Data Index: 313079 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.3061. Min Act: -0.1700

Data Index: 130538 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.3686. Min Act: -0.1700

Data Index: 935261 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.3686. Min Act: -0.1700

Data Index: 766569 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.3061. Min Act: -0.1700

Data Index: 1073653 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.2749. Min Act: -0.1700

Data Index: 84621 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.2749. Min Act: -0.1700

Data Index: 966587 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.3061. Min Act: -0.1700

Data Index: 582078 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.2749. Min Act: -0.1700

Data Index: 1181895 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 5.7749. Min Range: -5.7749

Max Act: 5.2749. Min Act: -0.1700

Data Index: 1223368 (C4 (Web Text))

Max Activating Token Index: 660