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

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

Neuron 546 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: 3.7449. Min Range: -3.7449

Max Act: 3.7136. Min Act: -0.1700

Data Index: 1232074 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.7449. Min Act: -0.1700

Data Index: 475616 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.6823. Min Act: -0.1700

Data Index: 1145237 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.6823. Min Act: -0.1700

Data Index: 603790 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.6823. Min Act: -0.1700

Data Index: 580005 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.6823. Min Act: -0.1700

Data Index: 735488 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.6510. Min Act: -0.1700

Data Index: 1365663 (Python Code)

Max Activating Token Index: 168

Text #7

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.6197. Min Act: -0.1700

Data Index: 207102 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.6510. Min Act: -0.1700

Data Index: 345473 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.6823. Min Act: -0.1700

Data Index: 857525 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.5883. Min Act: -0.1700

Data Index: 309727 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.6510. Min Act: -0.1700

Data Index: 246261 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.6197. Min Act: -0.1700

Data Index: 840135 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.5883. Min Act: -0.1700

Data Index: 969768 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.5883. Min Act: -0.1700

Data Index: 904192 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.5570. Min Act: -0.1700

Data Index: 100243 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.6197. Min Act: -0.1700

Data Index: 391009 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.6197. Min Act: -0.1700

Data Index: 132032 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.5883. Min Act: -0.1700

Data Index: 456044 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 3.7449. Min Range: -3.7449

Max Act: 3.5883. Min Act: -0.1700

Data Index: 1476949 (Python Code)

Max Activating Token Index: 675