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

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

Neuron 1612 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.3913. Min Act: -0.1700

Data Index: 1142281 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.2350. Min Act: -0.1700

Data Index: 1233816 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.1725. Min Act: -0.1700

Data Index: 441873 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.1413. Min Act: -0.1700

Data Index: 21501 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.0475. Min Act: -0.1700

Data Index: 898782 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.0475. Min Act: -0.1700

Data Index: 422492 (C4 (Web Text))

Max Activating Token Index: 298

Text #6

Max Range: 4.3913. Min Range: -4.3913

Max Act: 3.9850. Min Act: -0.1700

Data Index: 1288246 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.0475. Min Act: -0.1700

Data Index: 143456 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.1100. Min Act: -0.1700

Data Index: 990999 (C4 (Web Text))

Max Activating Token Index: 579

Text #9

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.0162. Min Act: -0.1700

Data Index: 1198584 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.0162. Min Act: -0.1700

Data Index: 103702 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 4.3913. Min Range: -4.3913

Max Act: 3.9224. Min Act: -0.1700

Data Index: 622836 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 4.3913. Min Range: -4.3913

Max Act: 3.9850. Min Act: -0.1700

Data Index: 579379 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.0162. Min Act: -0.1700

Data Index: 806776 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 4.3913. Min Range: -4.3913

Max Act: 3.9537. Min Act: -0.1700

Data Index: 174212 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 4.3913. Min Range: -4.3913

Max Act: 4.0162. Min Act: -0.1700

Data Index: 751472 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 4.3913. Min Range: -4.3913

Max Act: 3.9537. Min Act: -0.1700

Data Index: 640012 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 4.3913. Min Range: -4.3913

Max Act: 3.9537. Min Act: -0.1700

Data Index: 793459 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 4.3913. Min Range: -4.3913

Max Act: 3.9850. Min Act: -0.1700

Data Index: 984778 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 4.3913. Min Range: -4.3913

Max Act: 3.9850. Min Act: -0.1700

Data Index: 495473 (C4 (Web Text))

Max Activating Token Index: 453