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

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

Neuron 786 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.6573. Min Act: -0.1700

Data Index: 560600 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.5947. Min Act: -0.1700

Data Index: 558805 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.5947. Min Act: -0.1700

Data Index: 642357 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.5164. Min Act: -0.1700

Data Index: 835823 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.5477. Min Act: -0.1700

Data Index: 129420 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4850. Min Act: -0.1700

Data Index: 84 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.5007. Min Act: -0.1700

Data Index: 183855 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4850. Min Act: -0.1700

Data Index: 252739 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.5164. Min Act: -0.1700

Data Index: 1157908 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4693. Min Act: -0.1700

Data Index: 818726 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4223. Min Act: -0.1700

Data Index: 397648 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4537. Min Act: -0.1700

Data Index: 744025 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4380. Min Act: -0.1700

Data Index: 1253717 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4380. Min Act: -0.1700

Data Index: 1173174 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.4380. Min Act: -0.1700

Data Index: 1308553 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.3910. Min Act: -0.1700

Data Index: 1021227 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.3753. Min Act: -0.1700

Data Index: 976129 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.3910. Min Act: -0.1700

Data Index: 1184929 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.3753. Min Act: -0.1700

Data Index: 296782 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 3.6573. Min Range: -3.6573

Max Act: 3.3596. Min Act: -0.1700

Data Index: 1123426 (C4 (Web Text))

Max Activating Token Index: 497