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

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

Neuron 1284 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.8477. Min Act: -0.1700

Data Index: 700904 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.7539. Min Act: -0.1700

Data Index: 1054538 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.6757. Min Act: -0.1700

Data Index: 52282 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.6444. Min Act: -0.1700

Data Index: 556250 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5974. Min Act: -0.1700

Data Index: 363144 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5974. Min Act: -0.1700

Data Index: 126259 (C4 (Web Text))

Max Activating Token Index: 581

Text #6

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5974. Min Act: -0.1700

Data Index: 683303 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5817. Min Act: -0.1700

Data Index: 567314 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5974. Min Act: -0.1700

Data Index: 406219 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5661. Min Act: -0.1700

Data Index: 445982 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5817. Min Act: -0.1700

Data Index: 1159366 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5661. Min Act: -0.1700

Data Index: 152882 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5817. Min Act: -0.1700

Data Index: 960377 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5817. Min Act: -0.1700

Data Index: 1017855 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5504. Min Act: -0.1700

Data Index: 275943 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5661. Min Act: -0.1700

Data Index: 930763 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5348. Min Act: -0.1700

Data Index: 796306 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5504. Min Act: -0.1700

Data Index: 363865 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5348. Min Act: -0.1700

Data Index: 533930 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 3.8477. Min Range: -3.8477

Max Act: 3.5191. Min Act: -0.1700

Data Index: 370254 (C4 (Web Text))

Max Activating Token Index: 950