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

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

Neuron 1284 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1720. Min Range: -3.1720

Max Act: 3.1720. Min Act: -0.1700

Data Index: 329489 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 3.1720. Min Range: -3.1720

Max Act: 3.1090. Min Act: -0.1700

Data Index: 587170 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 3.1720. Min Range: -3.1720

Max Act: 3.0933. Min Act: -0.1700

Data Index: 1218649 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.9352. Min Act: -0.1700

Data Index: 1266797 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.9352. Min Act: -0.1679

Data Index: 615671 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.9194. Min Act: -0.1700

Data Index: 321469 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.8559. Min Act: -0.1700

Data Index: 1004640 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.8718. Min Act: -0.1700

Data Index: 1297086 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.8559. Min Act: -0.1700

Data Index: 350250 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.8559. Min Act: -0.1700

Data Index: 838574 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.8400. Min Act: -0.1700

Data Index: 701233 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.8241. Min Act: -0.1700

Data Index: 1173110 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.8400. Min Act: -0.1700

Data Index: 835631 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.8241. Min Act: -0.1700

Data Index: 776403 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.8082. Min Act: -0.1700

Data Index: 292631 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.7923. Min Act: -0.1700

Data Index: 852681 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.7923. Min Act: -0.1700

Data Index: 374524 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.8082. Min Act: -0.1700

Data Index: 907341 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.8082. Min Act: -0.1696

Data Index: 618305 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 3.1720. Min Range: -3.1720

Max Act: 2.8082. Min Act: -0.1700

Data Index: 502903 (C4 (Web Text))

Max Activating Token Index: 545