Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 856 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.5691. Min Act: -0.1700

Data Index: 862880 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.3810. Min Act: -0.1700

Data Index: 465280 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.3496. Min Act: -0.1700

Data Index: 512065 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.3182. Min Act: -0.1700

Data Index: 1166037 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.2868. Min Act: -0.1700

Data Index: 682824 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.3182. Min Act: -0.1700

Data Index: 1154690 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.2554. Min Act: -0.1700

Data Index: 1198572 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.2868. Min Act: -0.1700

Data Index: 775196 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.2711. Min Act: -0.1700

Data Index: 698935 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.2711. Min Act: -0.1700

Data Index: 325355 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.2240. Min Act: -0.1700

Data Index: 758069 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.2397. Min Act: -0.1700

Data Index: 22091 (C4 (Web Text))

Max Activating Token Index: 499

Text #12

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.2397. Min Act: -0.1700

Data Index: 787391 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.2397. Min Act: -0.1700

Data Index: 1119105 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.2240. Min Act: -0.1700

Data Index: 518238 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.2240. Min Act: -0.1700

Data Index: 693336 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.1768. Min Act: -0.1700

Data Index: 693956 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.1295. Min Act: -0.1700

Data Index: 1039272 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.1768. Min Act: -0.1700

Data Index: 107332 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 3.5691. Min Range: -3.5691

Max Act: 3.1610. Min Act: -0.1700

Data Index: 376589 (C4 (Web Text))

Max Activating Token Index: 683