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

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

Neuron 1275 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: 3.5349. Min Range: -3.5349

Max Act: 3.5349. Min Act: -0.1700

Data Index: 511855 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.4722. Min Act: -0.1700

Data Index: 322921 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.3782. Min Act: -0.1700

Data Index: 457324 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.3782. Min Act: -0.1700

Data Index: 1318544 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.3782. Min Act: -0.1700

Data Index: 46194 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.3782. Min Act: -0.1700

Data Index: 273080 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.3468. Min Act: -0.1700

Data Index: 629937 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.3468. Min Act: -0.1700

Data Index: 222014 (C4 (Web Text))

Max Activating Token Index: 162

Text #8

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.3154. Min Act: -0.1700

Data Index: 63061 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.2840. Min Act: -0.1700

Data Index: 728548 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.2840. Min Act: -0.1700

Data Index: 366910 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.3154. Min Act: -0.1699

Data Index: 476250 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.2840. Min Act: -0.1700

Data Index: 666913 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.2525. Min Act: -0.1700

Data Index: 1039107 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.2525. Min Act: -0.1700

Data Index: 220791 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.2211. Min Act: -0.1700

Data Index: 1127578 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.2840. Min Act: -0.1700

Data Index: 431051 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.1896. Min Act: -0.1700

Data Index: 946329 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.2525. Min Act: -0.1700

Data Index: 345768 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 3.5349. Min Range: -3.5349

Max Act: 3.2525. Min Act: -0.1700

Data Index: 384030 (C4 (Web Text))

Max Activating Token Index: 581