Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1288 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 4.1884. Min Range: -4.1884

Max Act: 4.1884. Min Act: -0.1700

Data Index: 1046948 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 4.1884. Min Range: -4.1884

Max Act: 4.1884. Min Act: -0.1700

Data Index: 911665 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 4.1884. Min Range: -4.1884

Max Act: 4.0321. Min Act: -0.1700

Data Index: 799743 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 4.1884. Min Range: -4.1884

Max Act: 4.0321. Min Act: -0.1700

Data Index: 167934 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 4.1884. Min Range: -4.1884

Max Act: 3.9695. Min Act: -0.1700

Data Index: 4234 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 4.1884. Min Range: -4.1884

Max Act: 3.9695. Min Act: -0.1700

Data Index: 832533 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 4.1884. Min Range: -4.1884

Max Act: 3.9070. Min Act: -0.1700

Data Index: 84852 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 4.1884. Min Range: -4.1884

Max Act: 3.9070. Min Act: -0.1700

Data Index: 1340280 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 4.1884. Min Range: -4.1884

Max Act: 3.8757. Min Act: -0.1700

Data Index: 67650 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 4.1884. Min Range: -4.1884

Max Act: 3.8444. Min Act: -0.1699

Data Index: 61393 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 4.1884. Min Range: -4.1884

Max Act: 3.9383. Min Act: -0.1700

Data Index: 211141 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 4.1884. Min Range: -4.1884

Max Act: 3.9695. Min Act: -0.1700

Data Index: 668286 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 4.1884. Min Range: -4.1884

Max Act: 3.8444. Min Act: -0.1700

Data Index: 457020 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 4.1884. Min Range: -4.1884

Max Act: 3.8132. Min Act: -0.1700

Data Index: 194759 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 4.1884. Min Range: -4.1884

Max Act: 3.8444. Min Act: -0.1700

Data Index: 1155009 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 4.1884. Min Range: -4.1884

Max Act: 3.8444. Min Act: -0.1700

Data Index: 56704 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 4.1884. Min Range: -4.1884

Max Act: 3.8444. Min Act: -0.1700

Data Index: 1133731 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 4.1884. Min Range: -4.1884

Max Act: 3.8757. Min Act: -0.1700

Data Index: 939692 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 4.1884. Min Range: -4.1884

Max Act: 3.8444. Min Act: -0.1700

Data Index: 217140 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 4.1884. Min Range: -4.1884

Max Act: 3.8444. Min Act: -0.1700

Data Index: 552221 (C4 (Web Text))

Max Activating Token Index: 452