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

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

Neuron 1019 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.4418. Min Act: -0.1700

Data Index: 328932 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3948. Min Act: -0.1700

Data Index: 1058678 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3477. Min Act: -0.1700

Data Index: 1054413 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3477. Min Act: -0.1700

Data Index: 822541 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3006. Min Act: -0.1700

Data Index: 299200 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3634. Min Act: -0.1700

Data Index: 573829 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3006. Min Act: -0.1700

Data Index: 244907 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3477. Min Act: -0.1700

Data Index: 415563 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3006. Min Act: -0.1700

Data Index: 322664 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2534. Min Act: -0.1700

Data Index: 93337 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3006. Min Act: -0.1700

Data Index: 744573 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.3163. Min Act: -0.1700

Data Index: 643425 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2849. Min Act: -0.1700

Data Index: 547152 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2849. Min Act: -0.1700

Data Index: 844264 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2377. Min Act: -0.1700

Data Index: 416441 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2692. Min Act: -0.1700

Data Index: 76052 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2377. Min Act: -0.1700

Data Index: 749108 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2377. Min Act: -0.1700

Data Index: 1069013 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2220. Min Act: -0.1700

Data Index: 929456 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 3.4418. Min Range: -3.4418

Max Act: 3.2849. Min Act: -0.1700

Data Index: 441628 (C4 (Web Text))

Max Activating Token Index: 306