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

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

Neuron 520 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: 3.5475. Min Range: -3.5475

Max Act: 3.5475. Min Act: -0.1698

Data Index: 99268 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 3.5475. Min Range: -3.5475

Max Act: 3.5475. Min Act: -0.1700

Data Index: 196723 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 3.5475. Min Range: -3.5475

Max Act: 3.5475. Min Act: -0.1700

Data Index: 495781 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 3.5475. Min Range: -3.5475

Max Act: 3.5161. Min Act: -0.1700

Data Index: 845917 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 3.5475. Min Range: -3.5475

Max Act: 3.4535. Min Act: -0.1700

Data Index: 1131827 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 3.5475. Min Range: -3.5475

Max Act: 3.4535. Min Act: -0.1700

Data Index: 1004092 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 3.5475. Min Range: -3.5475

Max Act: 3.4064. Min Act: -0.1700

Data Index: 1034775 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 3.5475. Min Range: -3.5475

Max Act: 3.4221. Min Act: -0.1700

Data Index: 700836 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 3.5475. Min Range: -3.5475

Max Act: 3.4378. Min Act: -0.1700

Data Index: 520408 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 3.5475. Min Range: -3.5475

Max Act: 3.4064. Min Act: -0.1700

Data Index: 1200274 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 3.5475. Min Range: -3.5475

Max Act: 3.4221. Min Act: -0.1700

Data Index: 1291727 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 3.5475. Min Range: -3.5475

Max Act: 3.3907. Min Act: -0.1700

Data Index: 330917 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 3.5475. Min Range: -3.5475

Max Act: 3.3750. Min Act: -0.1700

Data Index: 572944 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 3.5475. Min Range: -3.5475

Max Act: 3.3594. Min Act: -0.1700

Data Index: 1251659 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 3.5475. Min Range: -3.5475

Max Act: 3.3750. Min Act: -0.1700

Data Index: 1100568 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 3.5475. Min Range: -3.5475

Max Act: 3.3594. Min Act: -0.1700

Data Index: 920654 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 3.5475. Min Range: -3.5475

Max Act: 3.3437. Min Act: -0.1700

Data Index: 314641 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 3.5475. Min Range: -3.5475

Max Act: 3.3750. Min Act: -0.1700

Data Index: 1024519 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 3.5475. Min Range: -3.5475

Max Act: 3.3594. Min Act: -0.1700

Data Index: 288085 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 3.5475. Min Range: -3.5475

Max Act: 3.3123. Min Act: -0.1700

Data Index: 773734 (C4 (Web Text))

Max Activating Token Index: 170