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

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

Neuron 286 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3514. Min Range: -5.3514

Max Act: 5.3514. Min Act: -0.1700

Data Index: 197238 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 5.3514. Min Range: -5.3514

Max Act: 5.1639. Min Act: -0.1700

Data Index: 1125097 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 5.3514. Min Range: -5.3514

Max Act: 5.1795. Min Act: -0.1700

Data Index: 999576 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 5.3514. Min Range: -5.3514

Max Act: 5.1170. Min Act: -0.1700

Data Index: 249624 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 5.3514. Min Range: -5.3514

Max Act: 4.9920. Min Act: -0.1700

Data Index: 557786 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 5.3514. Min Range: -5.3514

Max Act: 4.9764. Min Act: -0.1700

Data Index: 672407 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 5.3514. Min Range: -5.3514

Max Act: 4.9764. Min Act: -0.1700

Data Index: 893790 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 5.3514. Min Range: -5.3514

Max Act: 4.9295. Min Act: -0.1700

Data Index: 329098 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 5.3514. Min Range: -5.3514

Max Act: 4.9764. Min Act: -0.1700

Data Index: 708430 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 5.3514. Min Range: -5.3514

Max Act: 4.8827. Min Act: -0.1700

Data Index: 592042 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 5.3514. Min Range: -5.3514

Max Act: 4.8670. Min Act: -0.1700

Data Index: 1202671 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 5.3514. Min Range: -5.3514

Max Act: 4.8670. Min Act: -0.1700

Data Index: 349712 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 5.3514. Min Range: -5.3514

Max Act: 4.8983. Min Act: -0.1699

Data Index: 819126 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 5.3514. Min Range: -5.3514

Max Act: 4.8514. Min Act: -0.1700

Data Index: 174427 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 5.3514. Min Range: -5.3514

Max Act: 4.7889. Min Act: -0.1700

Data Index: 381303 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 5.3514. Min Range: -5.3514

Max Act: 4.8045. Min Act: -0.1700

Data Index: 991071 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 5.3514. Min Range: -5.3514

Max Act: 4.7733. Min Act: -0.1700

Data Index: 352013 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 5.3514. Min Range: -5.3514

Max Act: 4.7577. Min Act: -0.1700

Data Index: 22110 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 5.3514. Min Range: -5.3514

Max Act: 4.7420. Min Act: -0.1700

Data Index: 680975 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 5.3514. Min Range: -5.3514

Max Act: 4.7889. Min Act: -0.1700

Data Index: 231777 (C4 (Web Text))

Max Activating Token Index: 92