Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1796 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.9177. Min Act: -0.1700

Data Index: 1604538 (Python Code)

Max Activating Token Index: 464

Text #1

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.8618. Min Act: -0.1700

Data Index: 1446132 (Python Code)

Max Activating Token Index: 340

Text #2

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.8803. Min Act: -0.1700

Data Index: 1419098 (Python Code)

Max Activating Token Index: 976

Text #3

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.8370. Min Act: -0.1700

Data Index: 1017357 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.8160. Min Act: -0.1700

Data Index: 1293290 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.7996. Min Act: -0.1700

Data Index: 1608140 (Python Code)

Max Activating Token Index: 247

Text #6

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.7850. Min Act: -0.1700

Data Index: 1417544 (Python Code)

Max Activating Token Index: 1002

Text #7

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.7842. Min Act: -0.1700

Data Index: 449684 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.7037. Min Act: -0.1700

Data Index: 785267 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.7212. Min Act: -0.1700

Data Index: 1300097 (C4 (Web Text))

Max Activating Token Index: 2

Text #10

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.7277. Min Act: -0.1700

Data Index: 745242 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.7224. Min Act: -0.1700

Data Index: 967719 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.7071. Min Act: -0.1700

Data Index: 357806 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.7050. Min Act: -0.1700

Data Index: 1636916 (Python Code)

Max Activating Token Index: 826

Text #14

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.6910. Min Act: -0.1700

Data Index: 1361611 (Python Code)

Max Activating Token Index: 931

Text #15

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.6707. Min Act: -0.1700

Data Index: 1526678 (Python Code)

Max Activating Token Index: 835

Text #16

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.6947. Min Act: -0.1700

Data Index: 652120 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.6760. Min Act: -0.1700

Data Index: 532280 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.6914. Min Act: -0.1700

Data Index: 1073184 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 3.9177. Min Range: -3.9177

Max Act: 3.6572. Min Act: -0.1700

Data Index: 405544 (C4 (Web Text))

Max Activating Token Index: 907