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

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

Neuron 1115 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: 3.9392. Min Range: -3.9392

Max Act: 3.9392. Min Act: -0.1700

Data Index: 1130867 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 3.9392. Min Range: -3.9392

Max Act: 3.8923. Min Act: -0.1700

Data Index: 791334 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 3.9392. Min Range: -3.9392

Max Act: 3.8923. Min Act: -0.1700

Data Index: 101967 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 3.9392. Min Range: -3.9392

Max Act: 3.8610. Min Act: -0.1700

Data Index: 1029799 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 3.9392. Min Range: -3.9392

Max Act: 3.8454. Min Act: -0.1700

Data Index: 1232468 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 3.9392. Min Range: -3.9392

Max Act: 3.7985. Min Act: -0.1700

Data Index: 1055972 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 3.9392. Min Range: -3.9392

Max Act: 3.7515. Min Act: -0.1700

Data Index: 620 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 3.9392. Min Range: -3.9392

Max Act: 3.8141. Min Act: -0.1700

Data Index: 108763 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 3.9392. Min Range: -3.9392

Max Act: 3.7985. Min Act: -0.1700

Data Index: 1220821 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 3.9392. Min Range: -3.9392

Max Act: 3.7672. Min Act: -0.1700

Data Index: 336141 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 3.9392. Min Range: -3.9392

Max Act: 3.7985. Min Act: -0.1700

Data Index: 660411 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 3.9392. Min Range: -3.9392

Max Act: 3.7359. Min Act: -0.1700

Data Index: 452980 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 3.9392. Min Range: -3.9392

Max Act: 3.7515. Min Act: -0.1700

Data Index: 823159 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 3.9392. Min Range: -3.9392

Max Act: 3.7515. Min Act: -0.1700

Data Index: 222079 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 3.9392. Min Range: -3.9392

Max Act: 3.7515. Min Act: -0.1700

Data Index: 399709 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 3.9392. Min Range: -3.9392

Max Act: 3.7046. Min Act: -0.1700

Data Index: 1056688 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 3.9392. Min Range: -3.9392

Max Act: 3.7046. Min Act: -0.1700

Data Index: 351987 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 3.9392. Min Range: -3.9392

Max Act: 3.7046. Min Act: -0.1700

Data Index: 1340686 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 3.9392. Min Range: -3.9392

Max Act: 3.6889. Min Act: -0.1700

Data Index: 666622 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 3.9392. Min Range: -3.9392

Max Act: 3.7046. Min Act: -0.1700

Data Index: 1146652 (C4 (Web Text))

Max Activating Token Index: 691