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

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

Neuron 387 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.5067. Min Act: -0.1700

Data Index: 475703 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.4753. Min Act: -0.1700

Data Index: 532275 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.4440. Min Act: -0.1700

Data Index: 335273 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.3656. Min Act: -0.1700

Data Index: 681961 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.3499. Min Act: -0.1700

Data Index: 417760 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.4126. Min Act: -0.1700

Data Index: 779609 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.3656. Min Act: -0.1700

Data Index: 1173520 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.3499. Min Act: -0.1700

Data Index: 852275 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.3499. Min Act: -0.1700

Data Index: 385856 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.3342. Min Act: -0.1700

Data Index: 26155 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.3342. Min Act: -0.1700

Data Index: 210844 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.3656. Min Act: -0.1700

Data Index: 112345 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.3185. Min Act: -0.1700

Data Index: 1282626 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.3342. Min Act: -0.1700

Data Index: 988373 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.3342. Min Act: -0.1700

Data Index: 997087 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.3185. Min Act: -0.1700

Data Index: 112713 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.3342. Min Act: -0.1700

Data Index: 270990 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.3185. Min Act: -0.1700

Data Index: 1254555 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.3342. Min Act: -0.1700

Data Index: 1139575 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 3.5067. Min Range: -3.5067

Max Act: 3.2871. Min Act: -0.1700

Data Index: 743795 (C4 (Web Text))

Max Activating Token Index: 420