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

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

Neuron 833 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: 5.3090. Min Range: -5.3090

Max Act: 5.3090. Min Act: -0.1700

Data Index: 1200765 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.1840. Min Act: -0.1700

Data Index: 328330 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.1527. Min Act: -0.1700

Data Index: 705682 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.1527. Min Act: -0.1700

Data Index: 73298 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.1527. Min Act: -0.1700

Data Index: 546765 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.0590. Min Act: -0.1700

Data Index: 909417 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.0902. Min Act: -0.1700

Data Index: 124284 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.0902. Min Act: -0.1700

Data Index: 760075 (C4 (Web Text))

Max Activating Token Index: 507

Text #8

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.0902. Min Act: -0.1700

Data Index: 953724 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.0590. Min Act: -0.1700

Data Index: 969777 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.0590. Min Act: -0.1700

Data Index: 716697 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.0902. Min Act: -0.1700

Data Index: 569495 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.0590. Min Act: -0.1700

Data Index: 38008 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.0277. Min Act: -0.1700

Data Index: 559329 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.0902. Min Act: -0.1700

Data Index: 1334167 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.0277. Min Act: -0.1700

Data Index: 993200 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.0277. Min Act: -0.1700

Data Index: 1213667 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 5.3090. Min Range: -5.3090

Max Act: 5.0277. Min Act: -0.1700

Data Index: 430615 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 5.3090. Min Range: -5.3090

Max Act: 4.9652. Min Act: -0.1700

Data Index: 621337 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 5.3090. Min Range: -5.3090

Max Act: 4.9965. Min Act: -0.1700

Data Index: 1083900 (C4 (Web Text))

Max Activating Token Index: 584