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

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

Neuron 691 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: 3.3197. Min Range: -3.3197

Max Act: 3.3165. Min Act: -0.1700

Data Index: 1129422 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 3.3197. Min Range: -3.3197

Max Act: 3.3197. Min Act: -0.1700

Data Index: 933958 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 3.3197. Min Range: -3.3197

Max Act: 3.3191. Min Act: -0.1700

Data Index: 131428 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 3.3197. Min Range: -3.3197

Max Act: 3.2943. Min Act: -0.1700

Data Index: 1251968 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 3.3197. Min Range: -3.3197

Max Act: 3.2460. Min Act: -0.1700

Data Index: 727975 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 3.3197. Min Range: -3.3197

Max Act: 3.2392. Min Act: -0.1700

Data Index: 450795 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 3.3197. Min Range: -3.3197

Max Act: 3.2297. Min Act: -0.1700

Data Index: 673816 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 3.3197. Min Range: -3.3197

Max Act: 3.2272. Min Act: -0.1700

Data Index: 1072001 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 3.3197. Min Range: -3.3197

Max Act: 3.2287. Min Act: -0.1700

Data Index: 86837 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 3.3197. Min Range: -3.3197

Max Act: 3.2163. Min Act: -0.1700

Data Index: 1044551 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 3.3197. Min Range: -3.3197

Max Act: 3.2089. Min Act: -0.1700

Data Index: 640872 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 3.3197. Min Range: -3.3197

Max Act: 3.1815. Min Act: -0.1700

Data Index: 653267 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 3.3197. Min Range: -3.3197

Max Act: 3.1900. Min Act: -0.1700

Data Index: 965677 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 3.3197. Min Range: -3.3197

Max Act: 3.1738. Min Act: -0.1700

Data Index: 220140 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 3.3197. Min Range: -3.3197

Max Act: 3.1544. Min Act: -0.1700

Data Index: 328293 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 3.3197. Min Range: -3.3197

Max Act: 3.1504. Min Act: -0.1700

Data Index: 514361 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 3.3197. Min Range: -3.3197

Max Act: 3.1703. Min Act: -0.1700

Data Index: 321519 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 3.3197. Min Range: -3.3197

Max Act: 3.1500. Min Act: -0.1700

Data Index: 1208494 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 3.3197. Min Range: -3.3197

Max Act: 3.1600. Min Act: -0.1700

Data Index: 676679 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 3.3197. Min Range: -3.3197

Max Act: 3.1629. Min Act: -0.1700

Data Index: 508830 (C4 (Web Text))

Max Activating Token Index: 285