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

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

Neuron 69 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: 7.1401. Min Range: -7.1401

Max Act: 6.7651. Min Act: -0.1700

Data Index: 371324 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 7.1401. Min Range: -7.1401

Max Act: 7.1401. Min Act: -0.1700

Data Index: 926538 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 7.1401. Min Range: -7.1401

Max Act: 6.8901. Min Act: -0.1700

Data Index: 312693 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 7.1401. Min Range: -7.1401

Max Act: 6.9526. Min Act: -0.1700

Data Index: 981226 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 7.1401. Min Range: -7.1401

Max Act: 6.8276. Min Act: -0.1700

Data Index: 909148 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 7.1401. Min Range: -7.1401

Max Act: 6.8901. Min Act: -0.1700

Data Index: 108806 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 7.1401. Min Range: -7.1401

Max Act: 6.7964. Min Act: -0.1700

Data Index: 705671 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 7.1401. Min Range: -7.1401

Max Act: 6.8901. Min Act: -0.1700

Data Index: 1049403 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 7.1401. Min Range: -7.1401

Max Act: 6.7964. Min Act: -0.1700

Data Index: 1131827 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 7.1401. Min Range: -7.1401

Max Act: 6.8589. Min Act: -0.1700

Data Index: 511564 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 7.1401. Min Range: -7.1401

Max Act: 6.6401. Min Act: -0.1700

Data Index: 249826 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 7.1401. Min Range: -7.1401

Max Act: 6.3901. Min Act: -0.1700

Data Index: 652171 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 7.1401. Min Range: -7.1401

Max Act: 6.6401. Min Act: -0.1700

Data Index: 940865 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 7.1401. Min Range: -7.1401

Max Act: 6.5776. Min Act: -0.1700

Data Index: 565567 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 7.1401. Min Range: -7.1401

Max Act: 6.3276. Min Act: -0.1700

Data Index: 1017249 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 7.1401. Min Range: -7.1401

Max Act: 6.3901. Min Act: -0.1700

Data Index: 80962 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 7.1401. Min Range: -7.1401

Max Act: 6.4526. Min Act: -0.1700

Data Index: 100410 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 7.1401. Min Range: -7.1401

Max Act: 6.4214. Min Act: -0.1700

Data Index: 909720 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 7.1401. Min Range: -7.1401

Max Act: 6.2964. Min Act: -0.1700

Data Index: 721210 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 7.1401. Min Range: -7.1401

Max Act: 6.3901. Min Act: -0.1700

Data Index: 303886 (C4 (Web Text))

Max Activating Token Index: 26