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

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

Neuron 1626 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: 3.6193. Min Range: -3.6193

Max Act: 3.6193. Min Act: -0.1700

Data Index: 662160 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 3.6193. Min Range: -3.6193

Max Act: 3.5892. Min Act: -0.1700

Data Index: 661385 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 3.6193. Min Range: -3.6193

Max Act: 3.5948. Min Act: -0.1699

Data Index: 491231 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 3.6193. Min Range: -3.6193

Max Act: 3.5686. Min Act: -0.1700

Data Index: 787195 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 3.6193. Min Range: -3.6193

Max Act: 3.5730. Min Act: -0.1700

Data Index: 259165 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 3.6193. Min Range: -3.6193

Max Act: 3.5474. Min Act: -0.1693

Data Index: 1103869 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 3.6193. Min Range: -3.6193

Max Act: 3.5590. Min Act: -0.1696

Data Index: 789203 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 3.6193. Min Range: -3.6193

Max Act: 3.5349. Min Act: -0.1700

Data Index: 1132311 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 3.6193. Min Range: -3.6193

Max Act: 3.5362. Min Act: -0.1700

Data Index: 419491 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 3.6193. Min Range: -3.6193

Max Act: 3.5045. Min Act: -0.1700

Data Index: 713892 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 3.6193. Min Range: -3.6193

Max Act: 3.5147. Min Act: -0.1700

Data Index: 415154 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 3.6193. Min Range: -3.6193

Max Act: 3.4990. Min Act: -0.1700

Data Index: 706484 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 3.6193. Min Range: -3.6193

Max Act: 3.4845. Min Act: -0.1700

Data Index: 236740 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 3.6193. Min Range: -3.6193

Max Act: 3.4900. Min Act: -0.1700

Data Index: 921889 (C4 (Web Text))

Max Activating Token Index: 391

Text #14

Max Range: 3.6193. Min Range: -3.6193

Max Act: 3.5028. Min Act: -0.1700

Data Index: 894416 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 3.6193. Min Range: -3.6193

Max Act: 3.4824. Min Act: -0.1700

Data Index: 393528 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 3.6193. Min Range: -3.6193

Max Act: 3.4832. Min Act: -0.1700

Data Index: 793754 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 3.6193. Min Range: -3.6193

Max Act: 3.4770. Min Act: -0.1700

Data Index: 1072300 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 3.6193. Min Range: -3.6193

Max Act: 3.4788. Min Act: -0.1699

Data Index: 673368 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 3.6193. Min Range: -3.6193

Max Act: 3.4820. Min Act: -0.1700

Data Index: 339251 (C4 (Web Text))

Max Activating Token Index: 18