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

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

Neuron 637 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: 5.0667. Min Range: -5.0667

Max Act: 5.0667. Min Act: -0.1700

Data Index: 1446968 (Python Code)

Max Activating Token Index: 928

Text #1

Max Range: 5.0667. Min Range: -5.0667

Max Act: 4.9747. Min Act: -0.1700

Data Index: 1629967 (Python Code)

Max Activating Token Index: 40

Text #2

Max Range: 5.0667. Min Range: -5.0667

Max Act: 4.9506. Min Act: -0.1700

Data Index: 472542 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 5.0667. Min Range: -5.0667

Max Act: 4.9467. Min Act: -0.1700

Data Index: 892460 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 5.0667. Min Range: -5.0667

Max Act: 4.9033. Min Act: -0.1700

Data Index: 1098799 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 5.0667. Min Range: -5.0667

Max Act: 4.9367. Min Act: -0.1700

Data Index: 361000 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 5.0667. Min Range: -5.0667

Max Act: 4.9076. Min Act: -0.1699

Data Index: 897963 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 5.0667. Min Range: -5.0667

Max Act: 4.9231. Min Act: -0.1700

Data Index: 4130 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 5.0667. Min Range: -5.0667

Max Act: 4.8866. Min Act: -0.1700

Data Index: 896201 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 5.0667. Min Range: -5.0667

Max Act: 4.8495. Min Act: -0.1700

Data Index: 200041 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 5.0667. Min Range: -5.0667

Max Act: 4.8534. Min Act: -0.1700

Data Index: 361889 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 5.0667. Min Range: -5.0667

Max Act: 4.8737. Min Act: -0.1700

Data Index: 726744 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 5.0667. Min Range: -5.0667

Max Act: 4.8856. Min Act: -0.1700

Data Index: 469485 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 5.0667. Min Range: -5.0667

Max Act: 4.9033. Min Act: -0.1700

Data Index: 894008 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 5.0667. Min Range: -5.0667

Max Act: 4.8811. Min Act: -0.1700

Data Index: 896586 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 5.0667. Min Range: -5.0667

Max Act: 4.8469. Min Act: -0.1700

Data Index: 478797 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 5.0667. Min Range: -5.0667

Max Act: 4.8828. Min Act: -0.1700

Data Index: 932261 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 5.0667. Min Range: -5.0667

Max Act: 4.8994. Min Act: -0.1700

Data Index: 962816 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 5.0667. Min Range: -5.0667

Max Act: 4.8735. Min Act: -0.1700

Data Index: 1243299 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 5.0667. Min Range: -5.0667

Max Act: 4.8715. Min Act: -0.1700

Data Index: 351267 (C4 (Web Text))

Max Activating Token Index: 575