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

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

Neuron 972 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: 4.7326. Min Range: -4.7326

Max Act: 4.7158. Min Act: -0.1700

Data Index: 395918 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 4.7326. Min Range: -4.7326

Max Act: 4.7326. Min Act: -0.1698

Data Index: 1618424 (Python Code)

Max Activating Token Index: 972

Text #2

Max Range: 4.7326. Min Range: -4.7326

Max Act: 4.6361. Min Act: -0.1697

Data Index: 58576 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 4.7326. Min Range: -4.7326

Max Act: 4.5278. Min Act: -0.1698

Data Index: 14958 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 4.7326. Min Range: -4.7326

Max Act: 4.3976. Min Act: -0.1700

Data Index: 1546097 (Python Code)

Max Activating Token Index: 129

Text #5

Max Range: 4.7326. Min Range: -4.7326

Max Act: 4.4040. Min Act: -0.1700

Data Index: 1404951 (Python Code)

Max Activating Token Index: 191

Text #6

Max Range: 4.7326. Min Range: -4.7326

Max Act: 4.3412. Min Act: -0.1699

Data Index: 1207997 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 4.7326. Min Range: -4.7326

Max Act: 4.2664. Min Act: -0.1692

Data Index: 861664 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 4.7326. Min Range: -4.7326

Max Act: 4.2514. Min Act: -0.1677

Data Index: 1648148 (Python Code)

Max Activating Token Index: 714

Text #9

Max Range: 4.7326. Min Range: -4.7326

Max Act: 4.2168. Min Act: -0.1700

Data Index: 1436510 (Python Code)

Max Activating Token Index: 618

Text #10

Max Range: 4.7326. Min Range: -4.7326

Max Act: 4.2442. Min Act: -0.1700

Data Index: 1593187 (Python Code)

Max Activating Token Index: 726

Text #11

Max Range: 4.7326. Min Range: -4.7326

Max Act: 4.2187. Min Act: -0.1700

Data Index: 1480485 (Python Code)

Max Activating Token Index: 773

Text #12

Max Range: 4.7326. Min Range: -4.7326

Max Act: 4.2196. Min Act: -0.1700

Data Index: 1561715 (Python Code)

Max Activating Token Index: 477

Text #13

Max Range: 4.7326. Min Range: -4.7326

Max Act: 4.2166. Min Act: -0.1698

Data Index: 1391421 (Python Code)

Max Activating Token Index: 115

Text #14

Max Range: 4.7326. Min Range: -4.7326

Max Act: 4.1950. Min Act: -0.1700

Data Index: 1621252 (Python Code)

Max Activating Token Index: 268

Text #15

Max Range: 4.7326. Min Range: -4.7326

Max Act: 4.2070. Min Act: -0.1699

Data Index: 1598546 (Python Code)

Max Activating Token Index: 467

Text #16

Max Range: 4.7326. Min Range: -4.7326

Max Act: 4.1766. Min Act: -0.1700

Data Index: 1364483 (Python Code)

Max Activating Token Index: 564

Text #17

Max Range: 4.7326. Min Range: -4.7326

Max Act: 4.1754. Min Act: -0.1700

Data Index: 1436904 (Python Code)

Max Activating Token Index: 832

Text #18

Max Range: 4.7326. Min Range: -4.7326

Max Act: 4.1569. Min Act: -0.1636

Data Index: 1537631 (Python Code)

Max Activating Token Index: 466

Text #19

Max Range: 4.7326. Min Range: -4.7326

Max Act: 4.1838. Min Act: -0.1687

Data Index: 1247490 (C4 (Web Text))

Max Activating Token Index: 450