Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 839 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.2463. Min Act: -0.1700

Data Index: 331723 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.2463. Min Act: -0.1700

Data Index: 881873 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.2306. Min Act: -0.1700

Data Index: 898308 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.2306. Min Act: -0.1700

Data Index: 253104 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.1677. Min Act: -0.1700

Data Index: 486758 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.1834. Min Act: -0.1700

Data Index: 1026302 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.1677. Min Act: -0.1700

Data Index: 742289 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.1519. Min Act: -0.1700

Data Index: 224106 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.1204. Min Act: -0.1700

Data Index: 137332 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.1204. Min Act: -0.1700

Data Index: 605064 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.1362. Min Act: -0.1700

Data Index: 683799 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.1362. Min Act: -0.1700

Data Index: 890271 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.1047. Min Act: -0.1700

Data Index: 619040 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.1204. Min Act: -0.1700

Data Index: 632390 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.0889. Min Act: -0.1700

Data Index: 378584 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.1204. Min Act: -0.1700

Data Index: 112019 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.1204. Min Act: -0.1700

Data Index: 582266 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.1047. Min Act: -0.1700

Data Index: 648468 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.0889. Min Act: -0.1700

Data Index: 1330612 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 3.2463. Min Range: -3.2463

Max Act: 3.1047. Min Act: -0.1700

Data Index: 351648 (C4 (Web Text))

Max Activating Token Index: 198