Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1528 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.7901. Min Act: -0.1700

Data Index: 215161 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.5401. Min Act: -0.1700

Data Index: 248508 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.4151. Min Act: -0.1700

Data Index: 505277 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.4151. Min Act: -0.1700

Data Index: 624628 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.3214. Min Act: -0.1700

Data Index: 274267 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.3214. Min Act: -0.1700

Data Index: 92199 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.2901. Min Act: -0.1700

Data Index: 1114016 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.2901. Min Act: -0.1700

Data Index: 24515 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.2589. Min Act: -0.1700

Data Index: 10156 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.2276. Min Act: -0.1700

Data Index: 12310 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.2276. Min Act: -0.1700

Data Index: 203879 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.1964. Min Act: -0.1700

Data Index: 506888 (C4 (Web Text))

Max Activating Token Index: 801

Text #12

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.1651. Min Act: -0.1700

Data Index: 64581 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.0714. Min Act: -0.1700

Data Index: 394186 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.1964. Min Act: -0.1700

Data Index: 600086 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.1339. Min Act: -0.1700

Data Index: 1276603 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.1339. Min Act: -0.1700

Data Index: 146290 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.0401. Min Act: -0.1700

Data Index: 743133 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.1339. Min Act: -0.1700

Data Index: 199195 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 5.7901. Min Range: -5.7901

Max Act: 5.0714. Min Act: -0.1700

Data Index: 51584 (C4 (Web Text))

Max Activating Token Index: 718