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

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

Neuron 854 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: 4.5797. Min Range: -4.5797

Max Act: 4.5786. Min Act: -0.1700

Data Index: 1632509 (Python Code)

Max Activating Token Index: 600

Text #1

Max Range: 4.5797. Min Range: -4.5797

Max Act: 4.5797. Min Act: -0.1700

Data Index: 466107 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 4.5797. Min Range: -4.5797

Max Act: 4.5050. Min Act: -0.1700

Data Index: 1072162 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 4.5797. Min Range: -4.5797

Max Act: 4.5005. Min Act: -0.1700

Data Index: 140291 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 4.5797. Min Range: -4.5797

Max Act: 4.4955. Min Act: -0.1700

Data Index: 389050 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 4.5797. Min Range: -4.5797

Max Act: 4.4888. Min Act: -0.1700

Data Index: 896579 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 4.5797. Min Range: -4.5797

Max Act: 4.4633. Min Act: -0.1700

Data Index: 656968 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 4.5797. Min Range: -4.5797

Max Act: 4.4910. Min Act: -0.1700

Data Index: 1454431 (Python Code)

Max Activating Token Index: 195

Text #8

Max Range: 4.5797. Min Range: -4.5797

Max Act: 4.4698. Min Act: -0.1700

Data Index: 1338457 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 4.5797. Min Range: -4.5797

Max Act: 4.4331. Min Act: -0.1700

Data Index: 1302357 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 4.5797. Min Range: -4.5797

Max Act: 4.4326. Min Act: -0.1700

Data Index: 1351479 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 4.5797. Min Range: -4.5797

Max Act: 4.4812. Min Act: -0.1700

Data Index: 441830 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 4.5797. Min Range: -4.5797

Max Act: 4.4597. Min Act: -0.1700

Data Index: 56294 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 4.5797. Min Range: -4.5797

Max Act: 4.4660. Min Act: -0.1700

Data Index: 597322 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 4.5797. Min Range: -4.5797

Max Act: 4.4052. Min Act: -0.1700

Data Index: 1137569 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 4.5797. Min Range: -4.5797

Max Act: 4.4646. Min Act: -0.1700

Data Index: 577436 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 4.5797. Min Range: -4.5797

Max Act: 4.4201. Min Act: -0.1700

Data Index: 847726 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 4.5797. Min Range: -4.5797

Max Act: 4.4287. Min Act: -0.1700

Data Index: 107110 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 4.5797. Min Range: -4.5797

Max Act: 4.4392. Min Act: -0.1700

Data Index: 1271095 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 4.5797. Min Range: -4.5797

Max Act: 4.4374. Min Act: -0.1700

Data Index: 336734 (C4 (Web Text))

Max Activating Token Index: 815