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

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

Neuron 1702 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: 3.9353. Min Range: -3.9353

Max Act: 3.9353. Min Act: -0.1700

Data Index: 111896 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 3.9353. Min Range: -3.9353

Max Act: 3.8727. Min Act: -0.1700

Data Index: 644530 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 3.9353. Min Range: -3.9353

Max Act: 3.8102. Min Act: -0.1700

Data Index: 643453 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 3.9353. Min Range: -3.9353

Max Act: 3.7632. Min Act: -0.1700

Data Index: 978847 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 3.9353. Min Range: -3.9353

Max Act: 3.6850. Min Act: -0.1700

Data Index: 585625 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 3.9353. Min Range: -3.9353

Max Act: 3.7319. Min Act: -0.1700

Data Index: 1303162 (C4 (Web Text))

Max Activating Token Index: 784

Text #6

Max Range: 3.9353. Min Range: -3.9353

Max Act: 3.7006. Min Act: -0.1700

Data Index: 714088 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 3.9353. Min Range: -3.9353

Max Act: 3.6067. Min Act: -0.1700

Data Index: 1080990 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 3.9353. Min Range: -3.9353

Max Act: 3.6380. Min Act: -0.1700

Data Index: 826332 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 3.9353. Min Range: -3.9353

Max Act: 3.5911. Min Act: -0.1700

Data Index: 922157 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 3.9353. Min Range: -3.9353

Max Act: 3.6067. Min Act: -0.1700

Data Index: 472475 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 3.9353. Min Range: -3.9353

Max Act: 3.6067. Min Act: -0.1700

Data Index: 57413 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 3.9353. Min Range: -3.9353

Max Act: 3.5911. Min Act: -0.1700

Data Index: 583374 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 3.9353. Min Range: -3.9353

Max Act: 3.6067. Min Act: -0.1700

Data Index: 404307 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 3.9353. Min Range: -3.9353

Max Act: 3.6067. Min Act: -0.1700

Data Index: 706582 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 3.9353. Min Range: -3.9353

Max Act: 3.6067. Min Act: -0.1700

Data Index: 881226 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 3.9353. Min Range: -3.9353

Max Act: 3.5598. Min Act: -0.1700

Data Index: 633652 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 3.9353. Min Range: -3.9353

Max Act: 3.5598. Min Act: -0.1700

Data Index: 470623 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 3.9353. Min Range: -3.9353

Max Act: 3.6067. Min Act: -0.1700

Data Index: 701146 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 3.9353. Min Range: -3.9353

Max Act: 3.5911. Min Act: -0.1700

Data Index: 379318 (C4 (Web Text))

Max Activating Token Index: 109