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

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

Neuron 2032 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: 3.7110. Min Range: -3.7110

Max Act: 3.7110. Min Act: -0.1700

Data Index: 1501723 (Python Code)

Max Activating Token Index: 1020

Text #1

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.5839. Min Act: -0.1700

Data Index: 1375891 (Python Code)

Max Activating Token Index: 26

Text #2

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.5789. Min Act: -0.1700

Data Index: 1582711 (Python Code)

Max Activating Token Index: 731

Text #3

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.5479. Min Act: -0.1700

Data Index: 1596448 (Python Code)

Max Activating Token Index: 49

Text #4

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.5159. Min Act: -0.1700

Data Index: 1556490 (Python Code)

Max Activating Token Index: 595

Text #5

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.4884. Min Act: -0.1700

Data Index: 1425689 (Python Code)

Max Activating Token Index: 165

Text #6

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.4887. Min Act: -0.1700

Data Index: 1451623 (Python Code)

Max Activating Token Index: 668

Text #7

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.4718. Min Act: -0.1700

Data Index: 1583626 (Python Code)

Max Activating Token Index: 773

Text #8

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.4731. Min Act: -0.1700

Data Index: 1501737 (Python Code)

Max Activating Token Index: 96

Text #9

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.4576. Min Act: -0.1700

Data Index: 1620842 (Python Code)

Max Activating Token Index: 440

Text #10

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.4737. Min Act: -0.1700

Data Index: 1561825 (Python Code)

Max Activating Token Index: 1020

Text #11

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.4310. Min Act: -0.1700

Data Index: 1507905 (Python Code)

Max Activating Token Index: 371

Text #12

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.4362. Min Act: -0.1700

Data Index: 1584906 (Python Code)

Max Activating Token Index: 23

Text #13

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.4366. Min Act: -0.1700

Data Index: 1565179 (Python Code)

Max Activating Token Index: 683

Text #14

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.4367. Min Act: -0.1700

Data Index: 984583 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.4212. Min Act: -0.1700

Data Index: 1424593 (Python Code)

Max Activating Token Index: 301

Text #16

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.4156. Min Act: -0.1700

Data Index: 1460374 (Python Code)

Max Activating Token Index: 287

Text #17

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.4145. Min Act: -0.1700

Data Index: 1645237 (Python Code)

Max Activating Token Index: 651

Text #18

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.3948. Min Act: -0.1700

Data Index: 1471429 (Python Code)

Max Activating Token Index: 16

Text #19

Max Range: 3.7110. Min Range: -3.7110

Max Act: 3.3858. Min Act: -0.1700

Data Index: 1427294 (Python Code)

Max Activating Token Index: 169