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

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

Neuron 1165 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: 7.2355. Min Range: -7.2355

Max Act: 7.1730. Min Act: -0.1700

Data Index: 606682 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 7.2355. Min Range: -7.2355

Max Act: 7.2355. Min Act: -0.1700

Data Index: 379661 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 7.2355. Min Range: -7.2355

Max Act: 7.0168. Min Act: -0.1700

Data Index: 781310 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 7.2355. Min Range: -7.2355

Max Act: 6.8918. Min Act: -0.1700

Data Index: 1271336 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 7.2355. Min Range: -7.2355

Max Act: 6.8918. Min Act: -0.1700

Data Index: 104432 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 7.2355. Min Range: -7.2355

Max Act: 6.8293. Min Act: -0.1700

Data Index: 191603 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 7.2355. Min Range: -7.2355

Max Act: 6.7668. Min Act: -0.1700

Data Index: 915506 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 7.2355. Min Range: -7.2355

Max Act: 6.7355. Min Act: -0.1700

Data Index: 600800 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 7.2355. Min Range: -7.2355

Max Act: 6.6418. Min Act: -0.1700

Data Index: 819548 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 7.2355. Min Range: -7.2355

Max Act: 6.6730. Min Act: -0.1700

Data Index: 653824 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 7.2355. Min Range: -7.2355

Max Act: 6.7043. Min Act: -0.1700

Data Index: 1250495 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 7.2355. Min Range: -7.2355

Max Act: 6.6730. Min Act: -0.1700

Data Index: 1181569 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 7.2355. Min Range: -7.2355

Max Act: 6.6418. Min Act: -0.1700

Data Index: 311711 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 7.2355. Min Range: -7.2355

Max Act: 6.6418. Min Act: -0.1700

Data Index: 1050016 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 7.2355. Min Range: -7.2355

Max Act: 6.5793. Min Act: -0.1700

Data Index: 44854 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 7.2355. Min Range: -7.2355

Max Act: 6.6105. Min Act: -0.1700

Data Index: 838606 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 7.2355. Min Range: -7.2355

Max Act: 6.5480. Min Act: -0.1694

Data Index: 370194 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 7.2355. Min Range: -7.2355

Max Act: 6.5793. Min Act: -0.1700

Data Index: 667807 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 7.2355. Min Range: -7.2355

Max Act: 6.5793. Min Act: -0.1700

Data Index: 106724 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 7.2355. Min Range: -7.2355

Max Act: 6.5480. Min Act: -0.1699

Data Index: 309577 (C4 (Web Text))

Max Activating Token Index: 141