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

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

Neuron 273 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: 3.9714. Min Range: -3.9714

Max Act: 3.9714. Min Act: -0.1700

Data Index: 132150 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.8843. Min Act: -0.1700

Data Index: 438406 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.8887. Min Act: -0.1698

Data Index: 1431023 (Python Code)

Max Activating Token Index: 529

Text #3

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.8801. Min Act: -0.1700

Data Index: 21328 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.7633. Min Act: -0.1700

Data Index: 1476329 (Python Code)

Max Activating Token Index: 939

Text #5

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.6525. Min Act: -0.1700

Data Index: 135643 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.6503. Min Act: -0.1470

Data Index: 1387453 (Python Code)

Max Activating Token Index: 992

Text #7

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.6518. Min Act: -0.1700

Data Index: 1344357 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.6234. Min Act: -0.1696

Data Index: 1490284 (Python Code)

Max Activating Token Index: 439

Text #9

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.5993. Min Act: -0.1700

Data Index: 1636277 (Python Code)

Max Activating Token Index: 175

Text #10

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.5917. Min Act: -0.1700

Data Index: 886810 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.5641. Min Act: -0.1700

Data Index: 912527 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.5334. Min Act: -0.1700

Data Index: 1528811 (Python Code)

Max Activating Token Index: 218

Text #13

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.5574. Min Act: -0.1700

Data Index: 1578276 (Python Code)

Max Activating Token Index: 773

Text #14

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.5005. Min Act: -0.1700

Data Index: 1072505 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.5159. Min Act: -0.1700

Data Index: 1615193 (Python Code)

Max Activating Token Index: 622

Text #16

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.5320. Min Act: -0.1700

Data Index: 835167 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.4895. Min Act: -0.1700

Data Index: 1480725 (Python Code)

Max Activating Token Index: 763

Text #18

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.4863. Min Act: -0.1699

Data Index: 1160131 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.5009. Min Act: -0.1584

Data Index: 1628636 (Python Code)

Max Activating Token Index: 546