Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1219 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.5463. Min Act: -0.1700

Data Index: 808792 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.5463. Min Act: -0.1700

Data Index: 138876 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.5463. Min Act: -0.1700

Data Index: 1095639 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.5306. Min Act: -0.1700

Data Index: 107427 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.4993. Min Act: -0.1700

Data Index: 1322044 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.4993. Min Act: -0.1700

Data Index: 912552 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.5306. Min Act: -0.1700

Data Index: 1143634 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.4836. Min Act: -0.1700

Data Index: 253035 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.4836. Min Act: -0.1700

Data Index: 702991 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.4679. Min Act: -0.1700

Data Index: 867656 (C4 (Web Text))

Max Activating Token Index: 846

Text #10

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.4679. Min Act: -0.1700

Data Index: 200684 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.4679. Min Act: -0.1700

Data Index: 231808 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.4836. Min Act: -0.1700

Data Index: 584283 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.4523. Min Act: -0.1700

Data Index: 98804 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.4523. Min Act: -0.1700

Data Index: 1177501 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.4679. Min Act: -0.1700

Data Index: 231207 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.4836. Min Act: -0.1700

Data Index: 158167 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.4836. Min Act: -0.1700

Data Index: 952344 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.4679. Min Act: -0.1700

Data Index: 1084499 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 3.5463. Min Range: -3.5463

Max Act: 3.4523. Min Act: -0.1700

Data Index: 1191084 (C4 (Web Text))

Max Activating Token Index: 213