Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 25 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.3357. Min Range: -7.3357

Max Act: 7.3357. Min Act: -0.1700

Data Index: 176912 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 7.3357. Min Range: -7.3357

Max Act: 6.8670. Min Act: -0.1699

Data Index: 1069153 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 7.3357. Min Range: -7.3357

Max Act: 6.6482. Min Act: -0.1700

Data Index: 873134 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 7.3357. Min Range: -7.3357

Max Act: 6.7107. Min Act: -0.1700

Data Index: 354386 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 7.3357. Min Range: -7.3357

Max Act: 6.7107. Min Act: -0.1700

Data Index: 798596 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 7.3357. Min Range: -7.3357

Max Act: 6.7107. Min Act: -0.1700

Data Index: 878142 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 7.3357. Min Range: -7.3357

Max Act: 6.6795. Min Act: -0.1700

Data Index: 558001 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 7.3357. Min Range: -7.3357

Max Act: 6.6482. Min Act: -0.1700

Data Index: 47762 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 7.3357. Min Range: -7.3357

Max Act: 6.6795. Min Act: -0.1700

Data Index: 663686 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 7.3357. Min Range: -7.3357

Max Act: 6.6170. Min Act: -0.1700

Data Index: 20128 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 7.3357. Min Range: -7.3357

Max Act: 6.6170. Min Act: -0.1700

Data Index: 4663 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 7.3357. Min Range: -7.3357

Max Act: 6.5857. Min Act: -0.1700

Data Index: 496105 (C4 (Web Text))

Max Activating Token Index: 52

Text #12

Max Range: 7.3357. Min Range: -7.3357

Max Act: 6.6170. Min Act: -0.1700

Data Index: 857222 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 7.3357. Min Range: -7.3357

Max Act: 6.6482. Min Act: -0.1700

Data Index: 863730 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 7.3357. Min Range: -7.3357

Max Act: 6.6170. Min Act: -0.1700

Data Index: 1297691 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 7.3357. Min Range: -7.3357

Max Act: 6.5545. Min Act: -0.1700

Data Index: 1249984 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 7.3357. Min Range: -7.3357

Max Act: 6.5857. Min Act: -0.1700

Data Index: 648985 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 7.3357. Min Range: -7.3357

Max Act: 6.6170. Min Act: -0.1700

Data Index: 360189 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 7.3357. Min Range: -7.3357

Max Act: 6.5857. Min Act: -0.1700

Data Index: 987660 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 7.3357. Min Range: -7.3357

Max Act: 6.5857. Min Act: -0.1699

Data Index: 470797 (C4 (Web Text))

Max Activating Token Index: 505