Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 565 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.9950. Min Act: -0.1700

Data Index: 360924 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.9481. Min Act: -0.1700

Data Index: 939153 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8856. Min Act: -0.1700

Data Index: 315759 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8387. Min Act: -0.1700

Data Index: 87854 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8856. Min Act: -0.1700

Data Index: 629783 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.9012. Min Act: -0.1700

Data Index: 686614 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8543. Min Act: -0.1700

Data Index: 817942 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8543. Min Act: -0.1700

Data Index: 1125227 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8230. Min Act: -0.1700

Data Index: 890776 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8387. Min Act: -0.1700

Data Index: 673268 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8074. Min Act: -0.1700

Data Index: 836652 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8230. Min Act: -0.1700

Data Index: 1116071 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8230. Min Act: -0.1700

Data Index: 230884 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8074. Min Act: -0.1700

Data Index: 955842 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8230. Min Act: -0.1700

Data Index: 1314722 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8543. Min Act: -0.1700

Data Index: 1107850 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8074. Min Act: -0.1700

Data Index: 201272 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8230. Min Act: -0.1700

Data Index: 655063 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.8074. Min Act: -0.1700

Data Index: 1087704 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 3.9950. Min Range: -3.9950

Max Act: 3.7761. Min Act: -0.1700

Data Index: 907375 (C4 (Web Text))

Max Activating Token Index: 315