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

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

Neuron 1393 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: 3.3102. Min Range: -3.3102

Max Act: 3.3102. Min Act: -0.1700

Data Index: 797136 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 3.3102. Min Range: -3.3102

Max Act: 3.2485. Min Act: -0.1700

Data Index: 22853 (C4 (Web Text))

Max Activating Token Index: 481

Text #2

Max Range: 3.3102. Min Range: -3.3102

Max Act: 3.2335. Min Act: -0.1700

Data Index: 1170719 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 3.3102. Min Range: -3.3102

Max Act: 3.2258. Min Act: -0.1700

Data Index: 152538 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 3.3102. Min Range: -3.3102

Max Act: 3.2245. Min Act: -0.1700

Data Index: 1534756 (Python Code)

Max Activating Token Index: 795

Text #5

Max Range: 3.3102. Min Range: -3.3102

Max Act: 3.1928. Min Act: -0.1700

Data Index: 1040190 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 3.3102. Min Range: -3.3102

Max Act: 3.1778. Min Act: -0.1700

Data Index: 1449180 (Python Code)

Max Activating Token Index: 871

Text #7

Max Range: 3.3102. Min Range: -3.3102

Max Act: 3.1781. Min Act: -0.1700

Data Index: 1462212 (Python Code)

Max Activating Token Index: 834

Text #8

Max Range: 3.3102. Min Range: -3.3102

Max Act: 3.1481. Min Act: -0.1700

Data Index: 476756 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 3.3102. Min Range: -3.3102

Max Act: 3.1451. Min Act: -0.1700

Data Index: 411792 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 3.3102. Min Range: -3.3102

Max Act: 3.1461. Min Act: -0.1700

Data Index: 1120075 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 3.3102. Min Range: -3.3102

Max Act: 3.1404. Min Act: -0.1700

Data Index: 205438 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 3.3102. Min Range: -3.3102

Max Act: 3.1199. Min Act: -0.1700

Data Index: 1294140 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 3.3102. Min Range: -3.3102

Max Act: 3.1321. Min Act: -0.1700

Data Index: 247634 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 3.3102. Min Range: -3.3102

Max Act: 3.1388. Min Act: -0.1700

Data Index: 1093370 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 3.3102. Min Range: -3.3102

Max Act: 3.1399. Min Act: -0.1700

Data Index: 331999 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 3.3102. Min Range: -3.3102

Max Act: 3.1329. Min Act: -0.1700

Data Index: 246282 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 3.3102. Min Range: -3.3102

Max Act: 3.1238. Min Act: -0.1700

Data Index: 297778 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 3.3102. Min Range: -3.3102

Max Act: 3.1133. Min Act: -0.1700

Data Index: 867609 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 3.3102. Min Range: -3.3102

Max Act: 3.1202. Min Act: -0.1700

Data Index: 311271 (C4 (Web Text))

Max Activating Token Index: 859