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

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

Neuron 279 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: 3.2455. Min Range: -3.2455

Max Act: 3.2455. Min Act: -0.1700

Data Index: 697704 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 3.2455. Min Range: -3.2455

Max Act: 3.2141. Min Act: -0.1700

Data Index: 1177757 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 3.2455. Min Range: -3.2455

Max Act: 3.1826. Min Act: -0.1700

Data Index: 1101115 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 3.2455. Min Range: -3.2455

Max Act: 3.1196. Min Act: -0.1700

Data Index: 304166 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 3.2455. Min Range: -3.2455

Max Act: 3.1039. Min Act: -0.1700

Data Index: 266985 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 3.2455. Min Range: -3.2455

Max Act: 3.1196. Min Act: -0.1700

Data Index: 1120517 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 3.2455. Min Range: -3.2455

Max Act: 3.0881. Min Act: -0.1700

Data Index: 188585 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 3.2455. Min Range: -3.2455

Max Act: 3.0250. Min Act: -0.1700

Data Index: 870595 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 3.2455. Min Range: -3.2455

Max Act: 3.0723. Min Act: -0.1700

Data Index: 980115 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 3.2455. Min Range: -3.2455

Max Act: 2.9934. Min Act: -0.1700

Data Index: 547457 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 3.2455. Min Range: -3.2455

Max Act: 2.9775. Min Act: -0.1700

Data Index: 823052 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 3.2455. Min Range: -3.2455

Max Act: 2.9775. Min Act: -0.1700

Data Index: 47816 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 3.2455. Min Range: -3.2455

Max Act: 2.9934. Min Act: -0.1700

Data Index: 864672 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 3.2455. Min Range: -3.2455

Max Act: 2.9617. Min Act: -0.1700

Data Index: 1243675 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 3.2455. Min Range: -3.2455

Max Act: 2.9300. Min Act: -0.1700

Data Index: 1161718 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 3.2455. Min Range: -3.2455

Max Act: 2.9300. Min Act: -0.1700

Data Index: 205329 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 3.2455. Min Range: -3.2455

Max Act: 3.0092. Min Act: -0.1700

Data Index: 1233649 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 3.2455. Min Range: -3.2455

Max Act: 2.9934. Min Act: -0.1700

Data Index: 797706 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 3.2455. Min Range: -3.2455

Max Act: 2.9459. Min Act: -0.1700

Data Index: 174566 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 3.2455. Min Range: -3.2455

Max Act: 2.9142. Min Act: -0.1700

Data Index: 1089187 (C4 (Web Text))

Max Activating Token Index: 643