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

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

Neuron 1683 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.5517. Min Act: -0.1700

Data Index: 819412 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.4892. Min Act: -0.1700

Data Index: 1052576 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.4580. Min Act: -0.1700

Data Index: 374494 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.3955. Min Act: -0.1700

Data Index: 124928 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.3330. Min Act: -0.1700

Data Index: 662627 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.3330. Min Act: -0.1700

Data Index: 1222675 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.3330. Min Act: -0.1700

Data Index: 1221655 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.3017. Min Act: -0.1700

Data Index: 1145502 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.3330. Min Act: -0.1700

Data Index: 1269989 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.2705. Min Act: -0.1700

Data Index: 845442 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.3017. Min Act: -0.1700

Data Index: 525549 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.3330. Min Act: -0.1700

Data Index: 718169 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.2705. Min Act: -0.1700

Data Index: 1266294 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.3017. Min Act: -0.1700

Data Index: 1082766 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.2705. Min Act: -0.1700

Data Index: 246798 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.2392. Min Act: -0.1700

Data Index: 453183 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.2392. Min Act: -0.1700

Data Index: 725060 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.2705. Min Act: -0.1700

Data Index: 1236119 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.2392. Min Act: -0.1700

Data Index: 679014 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 5.5517. Min Range: -5.5517

Max Act: 5.2080. Min Act: -0.1700

Data Index: 199012 (C4 (Web Text))

Max Activating Token Index: 1022