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

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

Neuron 1802 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: 3.9910. Min Range: -3.9910

Max Act: 3.9910. Min Act: -0.1700

Data Index: 22689 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.9546. Min Act: -0.1700

Data Index: 1650403 (Python Code)

Max Activating Token Index: 967

Text #2

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.8530. Min Act: -0.1700

Data Index: 735583 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.8443. Min Act: -0.1700

Data Index: 673892 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7675. Min Act: -0.1700

Data Index: 670289 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.8066. Min Act: -0.1700

Data Index: 409821 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7888. Min Act: -0.1700

Data Index: 1546090 (Python Code)

Max Activating Token Index: 392

Text #7

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7856. Min Act: -0.1700

Data Index: 1620066 (Python Code)

Max Activating Token Index: 864

Text #8

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7763. Min Act: -0.1700

Data Index: 519284 (C4 (Web Text))

Max Activating Token Index: 718

Text #9

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7543. Min Act: -0.1700

Data Index: 1310940 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7698. Min Act: -0.1700

Data Index: 1154500 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7632. Min Act: -0.1700

Data Index: 1333909 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7353. Min Act: -0.1700

Data Index: 779778 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7598. Min Act: -0.1700

Data Index: 357155 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7433. Min Act: -0.1700

Data Index: 526671 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7184. Min Act: -0.1700

Data Index: 347452 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7138. Min Act: -0.1700

Data Index: 1368551 (Python Code)

Max Activating Token Index: 188

Text #17

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7037. Min Act: -0.1700

Data Index: 739771 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7275. Min Act: -0.1700

Data Index: 1101772 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7116. Min Act: -0.1700

Data Index: 1380365 (Python Code)

Max Activating Token Index: 93