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

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

Neuron 725 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: 5.0138. Min Range: -5.0138

Max Act: 5.0138. Min Act: -0.1700

Data Index: 795113 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.9940. Min Act: -0.1700

Data Index: 1476791 (Python Code)

Max Activating Token Index: 960

Text #2

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.9886. Min Act: -0.1700

Data Index: 451818 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.8928. Min Act: -0.1699

Data Index: 460242 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.8296. Min Act: -0.1700

Data Index: 1191290 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.8136. Min Act: -0.1698

Data Index: 591456 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.8550. Min Act: -0.1700

Data Index: 794973 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.8191. Min Act: -0.1699

Data Index: 715574 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7685. Min Act: -0.1699

Data Index: 1621252 (Python Code)

Max Activating Token Index: 268

Text #9

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7828. Min Act: -0.1698

Data Index: 1337276 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7730. Min Act: -0.1700

Data Index: 1241789 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7525. Min Act: -0.1700

Data Index: 59424 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7208. Min Act: -0.1700

Data Index: 1247141 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7421. Min Act: -0.1699

Data Index: 487731 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7075. Min Act: -0.1700

Data Index: 641065 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7101. Min Act: -0.1700

Data Index: 761357 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7213. Min Act: -0.1700

Data Index: 659645 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7425. Min Act: -0.1675

Data Index: 16937 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7193. Min Act: -0.1693

Data Index: 1368410 (Python Code)

Max Activating Token Index: 580

Text #19

Max Range: 5.0138. Min Range: -5.0138

Max Act: 4.7080. Min Act: -0.1700

Data Index: 1404650 (Python Code)

Max Activating Token Index: 419