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

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

Neuron 1870 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: 3.3241. Min Range: -3.3241

Max Act: 3.3241. Min Act: -0.1700

Data Index: 1037712 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 3.3241. Min Range: -3.3241

Max Act: 3.2891. Min Act: -0.1700

Data Index: 659030 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 3.3241. Min Range: -3.3241

Max Act: 3.2599. Min Act: -0.1700

Data Index: 50488 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 3.3241. Min Range: -3.3241

Max Act: 3.2490. Min Act: -0.1700

Data Index: 462091 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 3.3241. Min Range: -3.3241

Max Act: 3.2503. Min Act: -0.1700

Data Index: 1066848 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 3.3241. Min Range: -3.3241

Max Act: 3.1850. Min Act: -0.1700

Data Index: 1177340 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 3.3241. Min Range: -3.3241

Max Act: 3.2015. Min Act: -0.1700

Data Index: 676401 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 3.3241. Min Range: -3.3241

Max Act: 3.1670. Min Act: -0.1700

Data Index: 803691 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 3.3241. Min Range: -3.3241

Max Act: 3.1613. Min Act: -0.1700

Data Index: 171130 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 3.3241. Min Range: -3.3241

Max Act: 3.1647. Min Act: -0.1700

Data Index: 1019593 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 3.3241. Min Range: -3.3241

Max Act: 3.1657. Min Act: -0.1700

Data Index: 688938 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 3.3241. Min Range: -3.3241

Max Act: 3.1296. Min Act: -0.1700

Data Index: 868845 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 3.3241. Min Range: -3.3241

Max Act: 3.1493. Min Act: -0.1700

Data Index: 1173819 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 3.3241. Min Range: -3.3241

Max Act: 3.1152. Min Act: -0.1700

Data Index: 1298930 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 3.3241. Min Range: -3.3241

Max Act: 3.1345. Min Act: -0.1700

Data Index: 612299 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 3.3241. Min Range: -3.3241

Max Act: 3.1246. Min Act: -0.1700

Data Index: 373776 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 3.3241. Min Range: -3.3241

Max Act: 3.1343. Min Act: -0.1700

Data Index: 420167 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 3.3241. Min Range: -3.3241

Max Act: 3.1113. Min Act: -0.1700

Data Index: 732518 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 3.3241. Min Range: -3.3241

Max Act: 3.1184. Min Act: -0.1700

Data Index: 613633 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 3.3241. Min Range: -3.3241

Max Act: 3.1010. Min Act: -0.1700

Data Index: 819957 (C4 (Web Text))

Max Activating Token Index: 245