Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1631 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.7392. Min Act: -0.1700

Data Index: 1602802 (Python Code)

Max Activating Token Index: 669

Text #1

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.7031. Min Act: -0.1700

Data Index: 1459664 (Python Code)

Max Activating Token Index: 548

Text #2

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.7201. Min Act: -0.1700

Data Index: 1638553 (Python Code)

Max Activating Token Index: 667

Text #3

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.6760. Min Act: -0.1700

Data Index: 1612884 (Python Code)

Max Activating Token Index: 783

Text #4

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.6285. Min Act: -0.1700

Data Index: 1515173 (Python Code)

Max Activating Token Index: 545

Text #5

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.6692. Min Act: -0.1700

Data Index: 1615878 (Python Code)

Max Activating Token Index: 596

Text #6

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.6321. Min Act: -0.1700

Data Index: 1649783 (Python Code)

Max Activating Token Index: 73

Text #7

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.6209. Min Act: -0.1700

Data Index: 1549160 (Python Code)

Max Activating Token Index: 689

Text #8

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.6325. Min Act: -0.1700

Data Index: 1469442 (Python Code)

Max Activating Token Index: 40

Text #9

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.5208. Min Act: -0.1700

Data Index: 1469617 (Python Code)

Max Activating Token Index: 975

Text #10

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.6289. Min Act: -0.1700

Data Index: 1431425 (Python Code)

Max Activating Token Index: 490

Text #11

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.6230. Min Act: -0.1700

Data Index: 1625288 (Python Code)

Max Activating Token Index: 307

Text #12

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.5849. Min Act: -0.1700

Data Index: 1620868 (Python Code)

Max Activating Token Index: 668

Text #13

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.5665. Min Act: -0.1700

Data Index: 1625246 (Python Code)

Max Activating Token Index: 330

Text #14

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.6209. Min Act: -0.1700

Data Index: 1602439 (Python Code)

Max Activating Token Index: 719

Text #15

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.5955. Min Act: -0.1700

Data Index: 1378336 (Python Code)

Max Activating Token Index: 977

Text #16

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.5572. Min Act: -0.1700

Data Index: 1578166 (Python Code)

Max Activating Token Index: 791

Text #17

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.5101. Min Act: -0.1700

Data Index: 1636747 (Python Code)

Max Activating Token Index: 953

Text #18

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.4959. Min Act: -0.1700

Data Index: 1463784 (Python Code)

Max Activating Token Index: 375

Text #19

Max Range: 3.7392. Min Range: -3.7392

Max Act: 3.5191. Min Act: -0.1700

Data Index: 1365457 (Python Code)

Max Activating Token Index: 353