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

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

Neuron 775 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: 3.2831. Min Range: -3.2831

Max Act: 3.2831. Min Act: -0.1700

Data Index: 114606 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 3.2831. Min Range: -3.2831

Max Act: 3.1730. Min Act: -0.1700

Data Index: 371888 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 3.2831. Min Range: -3.2831

Max Act: 3.1730. Min Act: -0.1700

Data Index: 977702 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 3.2831. Min Range: -3.2831

Max Act: 3.1888. Min Act: -0.1700

Data Index: 324992 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 3.2831. Min Range: -3.2831

Max Act: 3.0942. Min Act: -0.1700

Data Index: 1110467 (C4 (Web Text))

Max Activating Token Index: 633

Text #5

Max Range: 3.2831. Min Range: -3.2831

Max Act: 3.0785. Min Act: -0.1700

Data Index: 952910 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 3.2831. Min Range: -3.2831

Max Act: 3.0627. Min Act: -0.1700

Data Index: 1332720 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 3.2831. Min Range: -3.2831

Max Act: 3.0469. Min Act: -0.1700

Data Index: 454519 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 3.2831. Min Range: -3.2831

Max Act: 3.0785. Min Act: -0.1700

Data Index: 631822 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 3.2831. Min Range: -3.2831

Max Act: 3.0942. Min Act: -0.1700

Data Index: 604057 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 3.2831. Min Range: -3.2831

Max Act: 3.0469. Min Act: -0.1700

Data Index: 917272 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 3.2831. Min Range: -3.2831

Max Act: 3.0785. Min Act: -0.1700

Data Index: 172957 (C4 (Web Text))

Max Activating Token Index: 196

Text #12

Max Range: 3.2831. Min Range: -3.2831

Max Act: 3.0153. Min Act: -0.1700

Data Index: 608909 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 3.2831. Min Range: -3.2831

Max Act: 3.0785. Min Act: -0.1700

Data Index: 511406 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 3.2831. Min Range: -3.2831

Max Act: 3.0153. Min Act: -0.1700

Data Index: 463882 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 3.2831. Min Range: -3.2831

Max Act: 3.0942. Min Act: -0.1700

Data Index: 850300 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 3.2831. Min Range: -3.2831

Max Act: 3.0627. Min Act: -0.1700

Data Index: 149364 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 3.2831. Min Range: -3.2831

Max Act: 3.0311. Min Act: -0.1700

Data Index: 167625 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 3.2831. Min Range: -3.2831

Max Act: 3.0153. Min Act: -0.1700

Data Index: 1242128 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 3.2831. Min Range: -3.2831

Max Act: 3.0153. Min Act: -0.1700

Data Index: 903642 (C4 (Web Text))

Max Activating Token Index: 219