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

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

Neuron 1013 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.4249. Min Act: -0.1700

Data Index: 1090926 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.3935. Min Act: -0.1700

Data Index: 339830 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2994. Min Act: -0.1700

Data Index: 1091230 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2994. Min Act: -0.1700

Data Index: 82970 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2679. Min Act: -0.1700

Data Index: 1268319 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2679. Min Act: -0.1700

Data Index: 493869 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2679. Min Act: -0.1700

Data Index: 212092 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2679. Min Act: -0.1700

Data Index: 1186164 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2365. Min Act: -0.1700

Data Index: 875907 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2050. Min Act: -0.1700

Data Index: 399603 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.1736. Min Act: -0.1700

Data Index: 797882 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2050. Min Act: -0.1700

Data Index: 600260 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2365. Min Act: -0.1700

Data Index: 523648 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.2050. Min Act: -0.1700

Data Index: 37761 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.1421. Min Act: -0.1700

Data Index: 732616 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.1736. Min Act: -0.1700

Data Index: 540624 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.1736. Min Act: -0.1700

Data Index: 1267111 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.1421. Min Act: -0.1700

Data Index: 230345 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.1736. Min Act: -0.1700

Data Index: 288532 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 3.4249. Min Range: -3.4249

Max Act: 3.1421. Min Act: -0.1700

Data Index: 926732 (C4 (Web Text))

Max Activating Token Index: 205