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

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

Neuron 235 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: 4.1625. Min Range: -4.1625

Max Act: 4.1625. Min Act: -0.1700

Data Index: 38923 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 4.1625. Min Range: -4.1625

Max Act: 4.0098. Min Act: -0.1699

Data Index: 247787 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 4.1625. Min Range: -4.1625

Max Act: 3.9276. Min Act: -0.1700

Data Index: 784821 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 4.1625. Min Range: -4.1625

Max Act: 3.9029. Min Act: -0.1700

Data Index: 1099953 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 4.1625. Min Range: -4.1625

Max Act: 3.9056. Min Act: -0.1666

Data Index: 446320 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 4.1625. Min Range: -4.1625

Max Act: 3.8989. Min Act: -0.1700

Data Index: 442616 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 4.1625. Min Range: -4.1625

Max Act: 3.8202. Min Act: -0.1700

Data Index: 443097 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 4.1625. Min Range: -4.1625

Max Act: 3.7900. Min Act: -0.1700

Data Index: 540368 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 4.1625. Min Range: -4.1625

Max Act: 3.7837. Min Act: -0.1700

Data Index: 468506 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 4.1625. Min Range: -4.1625

Max Act: 3.7562. Min Act: -0.1700

Data Index: 1147150 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 4.1625. Min Range: -4.1625

Max Act: 3.7640. Min Act: -0.1700

Data Index: 817977 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 4.1625. Min Range: -4.1625

Max Act: 3.7408. Min Act: -0.1700

Data Index: 222824 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 4.1625. Min Range: -4.1625

Max Act: 3.7476. Min Act: -0.1700

Data Index: 833352 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 4.1625. Min Range: -4.1625

Max Act: 3.7302. Min Act: -0.1700

Data Index: 934805 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 4.1625. Min Range: -4.1625

Max Act: 3.7277. Min Act: -0.1700

Data Index: 622131 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 4.1625. Min Range: -4.1625

Max Act: 3.6920. Min Act: -0.1699

Data Index: 643564 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 4.1625. Min Range: -4.1625

Max Act: 3.6959. Min Act: -0.1700

Data Index: 923731 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 4.1625. Min Range: -4.1625

Max Act: 3.6665. Min Act: -0.1700

Data Index: 444962 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 4.1625. Min Range: -4.1625

Max Act: 3.6791. Min Act: -0.1700

Data Index: 833802 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 4.1625. Min Range: -4.1625

Max Act: 3.6830. Min Act: -0.1699

Data Index: 980557 (C4 (Web Text))

Max Activating Token Index: 582