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

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

Neuron 1728 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: 7.4412. Min Range: -7.4412

Max Act: 7.4412. Min Act: -0.1700

Data Index: 1105136 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 7.4412. Min Range: -7.4412

Max Act: 7.2537. Min Act: -0.1700

Data Index: 579831 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 7.4412. Min Range: -7.4412

Max Act: 7.2850. Min Act: -0.1700

Data Index: 893269 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 7.4412. Min Range: -7.4412

Max Act: 7.2537. Min Act: -0.1700

Data Index: 335476 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 7.4412. Min Range: -7.4412

Max Act: 7.2537. Min Act: -0.1700

Data Index: 711504 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 7.4412. Min Range: -7.4412

Max Act: 7.1600. Min Act: -0.1700

Data Index: 1098873 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 7.4412. Min Range: -7.4412

Max Act: 7.1912. Min Act: -0.1699

Data Index: 1081545 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 7.4412. Min Range: -7.4412

Max Act: 7.1287. Min Act: -0.1700

Data Index: 298796 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 7.4412. Min Range: -7.4412

Max Act: 7.1287. Min Act: -0.1700

Data Index: 218332 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 7.4412. Min Range: -7.4412

Max Act: 7.0975. Min Act: -0.1700

Data Index: 692370 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 7.4412. Min Range: -7.4412

Max Act: 7.0662. Min Act: -0.1700

Data Index: 1353927 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 7.4412. Min Range: -7.4412

Max Act: 7.1912. Min Act: -0.1700

Data Index: 254542 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 7.4412. Min Range: -7.4412

Max Act: 7.0350. Min Act: -0.1700

Data Index: 860163 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 7.4412. Min Range: -7.4412

Max Act: 7.0662. Min Act: -0.1700

Data Index: 668713 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 7.4412. Min Range: -7.4412

Max Act: 7.0350. Min Act: -0.1700

Data Index: 1084451 (C4 (Web Text))

Max Activating Token Index: 553

Text #15

Max Range: 7.4412. Min Range: -7.4412

Max Act: 7.0350. Min Act: -0.1700

Data Index: 1017051 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 7.4412. Min Range: -7.4412

Max Act: 7.0037. Min Act: -0.1697

Data Index: 414839 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 7.4412. Min Range: -7.4412

Max Act: 7.1287. Min Act: -0.1700

Data Index: 151602 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 7.4412. Min Range: -7.4412

Max Act: 7.0037. Min Act: -0.1700

Data Index: 253052 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 7.4412. Min Range: -7.4412

Max Act: 7.0350. Min Act: -0.1700

Data Index: 578795 (C4 (Web Text))

Max Activating Token Index: 685