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

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

Neuron 10 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5267. Min Range: -6.5267

Max Act: 6.5267. Min Act: -0.1700

Data Index: 1372470 (Python Code)

Max Activating Token Index: 244

Text #1

Max Range: 6.5267. Min Range: -6.5267

Max Act: 5.9642. Min Act: -0.1700

Data Index: 1323574 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 6.5267. Min Range: -6.5267

Max Act: 5.9329. Min Act: -0.1700

Data Index: 229849 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 6.5267. Min Range: -6.5267

Max Act: 5.9017. Min Act: -0.1700

Data Index: 1423316 (Python Code)

Max Activating Token Index: 32

Text #4

Max Range: 6.5267. Min Range: -6.5267

Max Act: 5.9017. Min Act: -0.1700

Data Index: 1545344 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 6.5267. Min Range: -6.5267

Max Act: 5.7142. Min Act: -0.1700

Data Index: 1441079 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 6.5267. Min Range: -6.5267

Max Act: 5.6204. Min Act: -0.1700

Data Index: 1494699 (Python Code)

Max Activating Token Index: 5

Text #7

Max Range: 6.5267. Min Range: -6.5267

Max Act: 5.5892. Min Act: -0.1700

Data Index: 1317486 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 6.5267. Min Range: -6.5267

Max Act: 5.4954. Min Act: -0.1700

Data Index: 157390 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 6.5267. Min Range: -6.5267

Max Act: 5.4954. Min Act: -0.1700

Data Index: 1411104 (Python Code)

Max Activating Token Index: 2

Text #10

Max Range: 6.5267. Min Range: -6.5267

Max Act: 5.4642. Min Act: -0.1700

Data Index: 1456205 (Python Code)

Max Activating Token Index: 2

Text #11

Max Range: 6.5267. Min Range: -6.5267

Max Act: 5.4329. Min Act: -0.1700

Data Index: 1049527 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 6.5267. Min Range: -6.5267

Max Act: 5.4329. Min Act: -0.1700

Data Index: 1429529 (Python Code)

Max Activating Token Index: 2

Text #13

Max Range: 6.5267. Min Range: -6.5267

Max Act: 5.4017. Min Act: -0.1700

Data Index: 1390734 (Python Code)

Max Activating Token Index: 930

Text #14

Max Range: 6.5267. Min Range: -6.5267

Max Act: 5.4017. Min Act: -0.1700

Data Index: 1389664 (Python Code)

Max Activating Token Index: 7

Text #15

Max Range: 6.5267. Min Range: -6.5267

Max Act: 5.4329. Min Act: -0.1700

Data Index: 1544585 (Python Code)

Max Activating Token Index: 2

Text #16

Max Range: 6.5267. Min Range: -6.5267

Max Act: 5.4017. Min Act: -0.1700

Data Index: 1651865 (Python Code)

Max Activating Token Index: 2

Text #17

Max Range: 6.5267. Min Range: -6.5267

Max Act: 5.4017. Min Act: -0.1700

Data Index: 1450836 (Python Code)

Max Activating Token Index: 3

Text #18

Max Range: 6.5267. Min Range: -6.5267

Max Act: 5.4329. Min Act: -0.1700

Data Index: 1016984 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 6.5267. Min Range: -6.5267

Max Act: 5.4017. Min Act: -0.1700

Data Index: 1498998 (Python Code)

Max Activating Token Index: 3