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

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

Neuron 875 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.2895. Min Act: -0.1700

Data Index: 323030 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.2109. Min Act: -0.1700

Data Index: 509750 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.2109. Min Act: -0.1700

Data Index: 1315313 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.2109. Min Act: -0.1700

Data Index: 801770 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.1637. Min Act: -0.1700

Data Index: 541089 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.1794. Min Act: -0.1700

Data Index: 344921 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.2109. Min Act: -0.1700

Data Index: 1279929 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.0849. Min Act: -0.1700

Data Index: 777086 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.0849. Min Act: -0.1700

Data Index: 1347207 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.1164. Min Act: -0.1700

Data Index: 68172 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 3.2895. Min Range: -3.2895

Max Act: 2.9901. Min Act: -0.1700

Data Index: 217904 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.0533. Min Act: -0.1700

Data Index: 1575082 (Python Code)

Max Activating Token Index: 878

Text #12

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.0533. Min Act: -0.1700

Data Index: 65353 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.0533. Min Act: -0.1700

Data Index: 1038139 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.1006. Min Act: -0.1700

Data Index: 1331747 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.0533. Min Act: -0.1700

Data Index: 59993 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.0059. Min Act: -0.1700

Data Index: 587191 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.0217. Min Act: -0.1700

Data Index: 1233946 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.0375. Min Act: -0.1700

Data Index: 687362 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 3.2895. Min Range: -3.2895

Max Act: 3.0375. Min Act: -0.1700

Data Index: 697466 (C4 (Web Text))

Max Activating Token Index: 560