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

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

Neuron 1442 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: 4.8611. Min Range: -4.8611

Max Act: 4.8611. Min Act: -0.1700

Data Index: 1558899 (Python Code)

Max Activating Token Index: 153

Text #1

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.4980. Min Act: -0.1700

Data Index: 696699 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.4544. Min Act: -0.1700

Data Index: 379834 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.4325. Min Act: -0.1700

Data Index: 1545315 (Python Code)

Max Activating Token Index: 119

Text #4

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.3977. Min Act: -0.1700

Data Index: 1576102 (Python Code)

Max Activating Token Index: 889

Text #5

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.3780. Min Act: -0.1696

Data Index: 627942 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.3635. Min Act: -0.1700

Data Index: 998462 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.3417. Min Act: -0.1700

Data Index: 1650213 (Python Code)

Max Activating Token Index: 190

Text #8

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.3392. Min Act: -0.1699

Data Index: 1612235 (Python Code)

Max Activating Token Index: 673

Text #9

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.2663. Min Act: -0.1700

Data Index: 1466214 (Python Code)

Max Activating Token Index: 672

Text #10

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.2498. Min Act: -0.1693

Data Index: 1319077 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.2368. Min Act: -0.1700

Data Index: 1563543 (Python Code)

Max Activating Token Index: 203

Text #12

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.2073. Min Act: -0.1700

Data Index: 270921 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.1707. Min Act: -0.1698

Data Index: 1566543 (Python Code)

Max Activating Token Index: 368

Text #14

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.1544. Min Act: -0.1695

Data Index: 1647325 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.1676. Min Act: -0.1700

Data Index: 520001 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.1351. Min Act: -0.1699

Data Index: 1641254 (Python Code)

Max Activating Token Index: 726

Text #17

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.1107. Min Act: -0.1700

Data Index: 1493686 (Python Code)

Max Activating Token Index: 121

Text #18

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.1065. Min Act: -0.1699

Data Index: 34420 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 4.8611. Min Range: -4.8611

Max Act: 4.0825. Min Act: -0.1700

Data Index: 1414255 (Python Code)

Max Activating Token Index: 225