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

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

Neuron 1027 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: 4.2563. Min Range: -4.2563

Max Act: 4.2563. Min Act: -0.1700

Data Index: 637891 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 4.2563. Min Range: -4.2563

Max Act: 4.2183. Min Act: -0.1700

Data Index: 1351670 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 4.2563. Min Range: -4.2563

Max Act: 4.1926. Min Act: -0.1700

Data Index: 794203 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 4.2563. Min Range: -4.2563

Max Act: 4.1690. Min Act: -0.1700

Data Index: 555061 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 4.2563. Min Range: -4.2563

Max Act: 4.1773. Min Act: -0.1699

Data Index: 738506 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 4.2563. Min Range: -4.2563

Max Act: 4.0925. Min Act: -0.1699

Data Index: 108493 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 4.2563. Min Range: -4.2563

Max Act: 4.0523. Min Act: -0.1683

Data Index: 416854 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 4.2563. Min Range: -4.2563

Max Act: 4.0457. Min Act: -0.1700

Data Index: 256045 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 4.2563. Min Range: -4.2563

Max Act: 4.0518. Min Act: -0.1700

Data Index: 778610 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 4.2563. Min Range: -4.2563

Max Act: 4.0280. Min Act: -0.1700

Data Index: 77932 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 4.2563. Min Range: -4.2563

Max Act: 4.0073. Min Act: -0.1700

Data Index: 1178418 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 4.2563. Min Range: -4.2563

Max Act: 4.0017. Min Act: -0.1700

Data Index: 1150728 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 4.2563. Min Range: -4.2563

Max Act: 4.0004. Min Act: -0.1699

Data Index: 4348 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 4.2563. Min Range: -4.2563

Max Act: 3.9858. Min Act: -0.1700

Data Index: 1260561 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 4.2563. Min Range: -4.2563

Max Act: 4.0009. Min Act: -0.1697

Data Index: 875715 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 4.2563. Min Range: -4.2563

Max Act: 3.9855. Min Act: -0.1700

Data Index: 818563 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 4.2563. Min Range: -4.2563

Max Act: 3.9618. Min Act: -0.1700

Data Index: 747367 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 4.2563. Min Range: -4.2563

Max Act: 3.9513. Min Act: -0.1700

Data Index: 246534 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 4.2563. Min Range: -4.2563

Max Act: 3.9652. Min Act: -0.1700

Data Index: 869620 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 4.2563. Min Range: -4.2563

Max Act: 3.9633. Min Act: -0.1700

Data Index: 653506 (C4 (Web Text))

Max Activating Token Index: 639