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

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

Neuron 418 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: 3.5434. Min Range: -3.5434

Max Act: 3.5434. Min Act: -0.1700

Data Index: 152077 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 3.5434. Min Range: -3.5434

Max Act: 3.4964. Min Act: -0.1700

Data Index: 174794 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 3.5434. Min Range: -3.5434

Max Act: 3.4494. Min Act: -0.1700

Data Index: 1628325 (Python Code)

Max Activating Token Index: 956

Text #3

Max Range: 3.5434. Min Range: -3.5434

Max Act: 3.4181. Min Act: -0.1700

Data Index: 1472533 (Python Code)

Max Activating Token Index: 683

Text #4

Max Range: 3.5434. Min Range: -3.5434

Max Act: 3.4494. Min Act: -0.1700

Data Index: 505025 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 3.5434. Min Range: -3.5434

Max Act: 3.4337. Min Act: -0.1700

Data Index: 871710 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 3.5434. Min Range: -3.5434

Max Act: 3.3867. Min Act: -0.1700

Data Index: 1606600 (Python Code)

Max Activating Token Index: 311

Text #7

Max Range: 3.5434. Min Range: -3.5434

Max Act: 3.3553. Min Act: -0.1700

Data Index: 334191 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 3.5434. Min Range: -3.5434

Max Act: 3.3710. Min Act: -0.1700

Data Index: 1612326 (Python Code)

Max Activating Token Index: 788

Text #9

Max Range: 3.5434. Min Range: -3.5434

Max Act: 3.3710. Min Act: -0.1700

Data Index: 1380568 (Python Code)

Max Activating Token Index: 583

Text #10

Max Range: 3.5434. Min Range: -3.5434

Max Act: 3.3710. Min Act: -0.1700

Data Index: 285756 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 3.5434. Min Range: -3.5434

Max Act: 3.3867. Min Act: -0.1700

Data Index: 1283440 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 3.5434. Min Range: -3.5434

Max Act: 3.3710. Min Act: -0.1700

Data Index: 1093835 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 3.5434. Min Range: -3.5434

Max Act: 3.4024. Min Act: -0.1700

Data Index: 493873 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 3.5434. Min Range: -3.5434

Max Act: 3.2454. Min Act: -0.1700

Data Index: 1584288 (Python Code)

Max Activating Token Index: 433

Text #15

Max Range: 3.5434. Min Range: -3.5434

Max Act: 3.2768. Min Act: -0.1700

Data Index: 1368282 (Python Code)

Max Activating Token Index: 218

Text #16

Max Range: 3.5434. Min Range: -3.5434

Max Act: 3.2611. Min Act: -0.1700

Data Index: 482944 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 3.5434. Min Range: -3.5434

Max Act: 3.2454. Min Act: -0.1700

Data Index: 831385 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 3.5434. Min Range: -3.5434

Max Act: 3.2296. Min Act: -0.1700

Data Index: 1428916 (Python Code)

Max Activating Token Index: 561

Text #19

Max Range: 3.5434. Min Range: -3.5434

Max Act: 3.2925. Min Act: -0.1700

Data Index: 1437892 (Python Code)

Max Activating Token Index: 952