Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1213 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.4634. Min Range: -4.4634

Max Act: 4.4634. Min Act: -0.1700

Data Index: 446075 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 4.4634. Min Range: -4.4634

Max Act: 4.2759. Min Act: -0.1700

Data Index: 505030 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 4.4634. Min Range: -4.4634

Max Act: 4.2759. Min Act: -0.1700

Data Index: 727705 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 4.4634. Min Range: -4.4634

Max Act: 4.1196. Min Act: -0.1700

Data Index: 1106154 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 4.4634. Min Range: -4.4634

Max Act: 4.0883. Min Act: -0.1700

Data Index: 551541 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 4.4634. Min Range: -4.4634

Max Act: 4.0571. Min Act: -0.1700

Data Index: 589562 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 4.4634. Min Range: -4.4634

Max Act: 3.9633. Min Act: -0.1700

Data Index: 443121 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 4.4634. Min Range: -4.4634

Max Act: 3.9633. Min Act: -0.1700

Data Index: 570295 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 4.4634. Min Range: -4.4634

Max Act: 3.9320. Min Act: -0.1700

Data Index: 892461 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 4.4634. Min Range: -4.4634

Max Act: 3.9633. Min Act: -0.1700

Data Index: 687102 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 4.4634. Min Range: -4.4634

Max Act: 3.9164. Min Act: -0.1700

Data Index: 594131 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 4.4634. Min Range: -4.4634

Max Act: 3.9007. Min Act: -0.1700

Data Index: 612436 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 4.4634. Min Range: -4.4634

Max Act: 3.8538. Min Act: -0.1700

Data Index: 567895 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 4.4634. Min Range: -4.4634

Max Act: 3.8069. Min Act: -0.1700

Data Index: 424790 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 4.4634. Min Range: -4.4634

Max Act: 3.8538. Min Act: -0.1700

Data Index: 563925 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 4.4634. Min Range: -4.4634

Max Act: 3.8382. Min Act: -0.1700

Data Index: 48266 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 4.4634. Min Range: -4.4634

Max Act: 3.8851. Min Act: -0.1700

Data Index: 868873 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 4.4634. Min Range: -4.4634

Max Act: 3.8538. Min Act: -0.1700

Data Index: 862966 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 4.4634. Min Range: -4.4634

Max Act: 3.8382. Min Act: -0.1700

Data Index: 656858 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 4.4634. Min Range: -4.4634

Max Act: 3.8538. Min Act: -0.1700

Data Index: 832497 (C4 (Web Text))

Max Activating Token Index: 570