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

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

Neuron 797 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: 5.7380. Min Range: -5.7380

Max Act: 5.7380. Min Act: -0.1700

Data Index: 570664 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 5.7380. Min Range: -5.7380

Max Act: 5.7068. Min Act: -0.1700

Data Index: 1256161 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 5.7380. Min Range: -5.7380

Max Act: 5.5818. Min Act: -0.1700

Data Index: 877084 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 5.7380. Min Range: -5.7380

Max Act: 5.5505. Min Act: -0.1700

Data Index: 347024 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 5.7380. Min Range: -5.7380

Max Act: 5.3630. Min Act: -0.1700

Data Index: 625628 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 5.7380. Min Range: -5.7380

Max Act: 5.3630. Min Act: -0.1700

Data Index: 1162970 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 5.7380. Min Range: -5.7380

Max Act: 5.3630. Min Act: -0.1700

Data Index: 497733 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 5.7380. Min Range: -5.7380

Max Act: 5.3318. Min Act: -0.1700

Data Index: 636593 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 5.7380. Min Range: -5.7380

Max Act: 5.3943. Min Act: -0.1700

Data Index: 1041397 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 5.7380. Min Range: -5.7380

Max Act: 5.3318. Min Act: -0.1700

Data Index: 496993 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 5.7380. Min Range: -5.7380

Max Act: 5.3005. Min Act: -0.1700

Data Index: 875653 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 5.7380. Min Range: -5.7380

Max Act: 5.3005. Min Act: -0.1700

Data Index: 442551 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 5.7380. Min Range: -5.7380

Max Act: 5.3005. Min Act: -0.1700

Data Index: 816504 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 5.7380. Min Range: -5.7380

Max Act: 5.3005. Min Act: -0.1700

Data Index: 808138 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 5.7380. Min Range: -5.7380

Max Act: 5.2693. Min Act: -0.1700

Data Index: 651593 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 5.7380. Min Range: -5.7380

Max Act: 5.2380. Min Act: -0.1700

Data Index: 618072 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 5.7380. Min Range: -5.7380

Max Act: 5.2380. Min Act: -0.1700

Data Index: 1185443 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 5.7380. Min Range: -5.7380

Max Act: 5.2693. Min Act: -0.1700

Data Index: 609946 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 5.7380. Min Range: -5.7380

Max Act: 5.3005. Min Act: -0.1700

Data Index: 125191 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 5.7380. Min Range: -5.7380

Max Act: 5.2693. Min Act: -0.1700

Data Index: 961118 (C4 (Web Text))

Max Activating Token Index: 613