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

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

Neuron 531 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: 3.3401. Min Range: -3.3401

Max Act: 3.3401. Min Act: -0.1700

Data Index: 89601 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 3.3401. Min Range: -3.3401

Max Act: 3.2630. Min Act: -0.1700

Data Index: 808617 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 3.3401. Min Range: -3.3401

Max Act: 3.2174. Min Act: -0.1700

Data Index: 1295988 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 3.3401. Min Range: -3.3401

Max Act: 3.2292. Min Act: -0.1700

Data Index: 112364 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 3.3401. Min Range: -3.3401

Max Act: 3.2011. Min Act: -0.1700

Data Index: 288749 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 3.3401. Min Range: -3.3401

Max Act: 3.1446. Min Act: -0.1700

Data Index: 588883 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 3.3401. Min Range: -3.3401

Max Act: 3.1411. Min Act: -0.1700

Data Index: 134892 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 3.3401. Min Range: -3.3401

Max Act: 3.1564. Min Act: -0.1700

Data Index: 1031398 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 3.3401. Min Range: -3.3401

Max Act: 3.1451. Min Act: -0.1700

Data Index: 728087 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 3.3401. Min Range: -3.3401

Max Act: 3.1472. Min Act: -0.1700

Data Index: 155213 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 3.3401. Min Range: -3.3401

Max Act: 3.1260. Min Act: -0.1700

Data Index: 32302 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 3.3401. Min Range: -3.3401

Max Act: 3.1274. Min Act: -0.1700

Data Index: 793300 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 3.3401. Min Range: -3.3401

Max Act: 3.1033. Min Act: -0.1700

Data Index: 104722 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 3.3401. Min Range: -3.3401

Max Act: 3.0890. Min Act: -0.1700

Data Index: 1247758 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 3.3401. Min Range: -3.3401

Max Act: 3.0587. Min Act: -0.1700

Data Index: 974172 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 3.3401. Min Range: -3.3401

Max Act: 3.0791. Min Act: -0.1700

Data Index: 830185 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 3.3401. Min Range: -3.3401

Max Act: 3.0775. Min Act: -0.1700

Data Index: 580584 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 3.3401. Min Range: -3.3401

Max Act: 3.0798. Min Act: -0.1700

Data Index: 686015 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 3.3401. Min Range: -3.3401

Max Act: 3.0602. Min Act: -0.1700

Data Index: 1071140 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 3.3401. Min Range: -3.3401

Max Act: 3.0754. Min Act: -0.1700

Data Index: 1153436 (C4 (Web Text))

Max Activating Token Index: 122