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

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

Neuron 112 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: 3.5195. Min Range: -3.5195

Max Act: 3.5195. Min Act: -0.1700

Data Index: 225117 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 3.5195. Min Range: -3.5195

Max Act: 3.4293. Min Act: -0.1700

Data Index: 267412 (C4 (Web Text))

Max Activating Token Index: 537

Text #2

Max Range: 3.5195. Min Range: -3.5195

Max Act: 3.3808. Min Act: -0.1673

Data Index: 26219 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 3.5195. Min Range: -3.5195

Max Act: 3.3386. Min Act: -0.1700

Data Index: 1098132 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 3.5195. Min Range: -3.5195

Max Act: 3.3208. Min Act: -0.1700

Data Index: 77391 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 3.5195. Min Range: -3.5195

Max Act: 3.2710. Min Act: -0.1700

Data Index: 312167 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 3.5195. Min Range: -3.5195

Max Act: 3.1950. Min Act: -0.1700

Data Index: 1613533 (Python Code)

Max Activating Token Index: 734

Text #7

Max Range: 3.5195. Min Range: -3.5195

Max Act: 3.2014. Min Act: -0.1700

Data Index: 134666 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 3.5195. Min Range: -3.5195

Max Act: 3.1904. Min Act: -0.1700

Data Index: 773000 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 3.5195. Min Range: -3.5195

Max Act: 3.1805. Min Act: -0.1700

Data Index: 61159 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 3.5195. Min Range: -3.5195

Max Act: 3.1506. Min Act: -0.1699

Data Index: 282667 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 3.5195. Min Range: -3.5195

Max Act: 3.1454. Min Act: -0.1700

Data Index: 1123277 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 3.5195. Min Range: -3.5195

Max Act: 3.1389. Min Act: -0.1699

Data Index: 874764 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 3.5195. Min Range: -3.5195

Max Act: 3.1344. Min Act: -0.1699

Data Index: 620774 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 3.5195. Min Range: -3.5195

Max Act: 3.1393. Min Act: -0.1699

Data Index: 822694 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 3.5195. Min Range: -3.5195

Max Act: 3.1370. Min Act: -0.1700

Data Index: 1463584 (Python Code)

Max Activating Token Index: 518

Text #16

Max Range: 3.5195. Min Range: -3.5195

Max Act: 3.1396. Min Act: -0.1699

Data Index: 1323518 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 3.5195. Min Range: -3.5195

Max Act: 3.1095. Min Act: -0.1700

Data Index: 274294 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 3.5195. Min Range: -3.5195

Max Act: 3.1122. Min Act: -0.1700

Data Index: 697276 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 3.5195. Min Range: -3.5195

Max Act: 3.0909. Min Act: -0.1691

Data Index: 1179073 (C4 (Web Text))

Max Activating Token Index: 948