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

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

Neuron 1168 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: 4.8406. Min Range: -4.8406

Max Act: 4.8406. Min Act: -0.1699

Data Index: 1452643 (Python Code)

Max Activating Token Index: 238

Text #1

Max Range: 4.8406. Min Range: -4.8406

Max Act: 4.7549. Min Act: -0.1698

Data Index: 1647682 (Python Code)

Max Activating Token Index: 593

Text #2

Max Range: 4.8406. Min Range: -4.8406

Max Act: 4.3864. Min Act: -0.1700

Data Index: 1646507 (Python Code)

Max Activating Token Index: 985

Text #3

Max Range: 4.8406. Min Range: -4.8406

Max Act: 4.3937. Min Act: -0.1700

Data Index: 1417653 (Python Code)

Max Activating Token Index: 932

Text #4

Max Range: 4.8406. Min Range: -4.8406

Max Act: 4.3063. Min Act: -0.1699

Data Index: 1594116 (Python Code)

Max Activating Token Index: 523

Text #5

Max Range: 4.8406. Min Range: -4.8406

Max Act: 4.3085. Min Act: -0.1698

Data Index: 1484882 (Python Code)

Max Activating Token Index: 109

Text #6

Max Range: 4.8406. Min Range: -4.8406

Max Act: 4.2220. Min Act: -0.1700

Data Index: 970221 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 4.8406. Min Range: -4.8406

Max Act: 4.2575. Min Act: -0.1700

Data Index: 1649246 (Python Code)

Max Activating Token Index: 955

Text #8

Max Range: 4.8406. Min Range: -4.8406

Max Act: 4.2457. Min Act: -0.1681

Data Index: 1644260 (Python Code)

Max Activating Token Index: 337

Text #9

Max Range: 4.8406. Min Range: -4.8406

Max Act: 4.2184. Min Act: -0.1700

Data Index: 1180417 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 4.8406. Min Range: -4.8406

Max Act: 4.1502. Min Act: -0.1683

Data Index: 1571735 (Python Code)

Max Activating Token Index: 490

Text #11

Max Range: 4.8406. Min Range: -4.8406

Max Act: 4.1235. Min Act: -0.1700

Data Index: 1652179 (Python Code)

Max Activating Token Index: 310

Text #12

Max Range: 4.8406. Min Range: -4.8406

Max Act: 4.1218. Min Act: -0.1699

Data Index: 1517346 (Python Code)

Max Activating Token Index: 81

Text #13

Max Range: 4.8406. Min Range: -4.8406

Max Act: 4.1245. Min Act: -0.1697

Data Index: 1574282 (Python Code)

Max Activating Token Index: 521

Text #14

Max Range: 4.8406. Min Range: -4.8406

Max Act: 4.1453. Min Act: -0.1681

Data Index: 1384613 (Python Code)

Max Activating Token Index: 149

Text #15

Max Range: 4.8406. Min Range: -4.8406

Max Act: 4.0914. Min Act: -0.1700

Data Index: 1582953 (Python Code)

Max Activating Token Index: 792

Text #16

Max Range: 4.8406. Min Range: -4.8406

Max Act: 4.0905. Min Act: -0.1700

Data Index: 1438614 (Python Code)

Max Activating Token Index: 529

Text #17

Max Range: 4.8406. Min Range: -4.8406

Max Act: 4.0798. Min Act: -0.1700

Data Index: 1416562 (Python Code)

Max Activating Token Index: 203

Text #18

Max Range: 4.8406. Min Range: -4.8406

Max Act: 4.0628. Min Act: -0.1699

Data Index: 411986 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 4.8406. Min Range: -4.8406

Max Act: 4.0880. Min Act: -0.1700

Data Index: 123788 (C4 (Web Text))

Max Activating Token Index: 74