Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1718 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1964. Min Range: -3.1964

Max Act: 3.1964. Min Act: -0.1700

Data Index: 825857 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 3.1964. Min Range: -3.1964

Max Act: 3.1335. Min Act: -0.1700

Data Index: 1217766 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 3.1964. Min Range: -3.1964

Max Act: 3.1177. Min Act: -0.1700

Data Index: 67569 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 3.1964. Min Range: -3.1964

Max Act: 3.1019. Min Act: -0.1700

Data Index: 1314732 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 3.1964. Min Range: -3.1964

Max Act: 3.1019. Min Act: -0.1700

Data Index: 282712 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 3.1964. Min Range: -3.1964

Max Act: 3.1019. Min Act: -0.1700

Data Index: 104969 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 3.1964. Min Range: -3.1964

Max Act: 3.0862. Min Act: -0.1700

Data Index: 958623 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 3.1964. Min Range: -3.1964

Max Act: 3.0862. Min Act: -0.1700

Data Index: 1038560 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 3.1964. Min Range: -3.1964

Max Act: 3.0072. Min Act: -0.1700

Data Index: 115953 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 3.1964. Min Range: -3.1964

Max Act: 3.0230. Min Act: -0.1700

Data Index: 681071 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 3.1964. Min Range: -3.1964

Max Act: 2.9756. Min Act: -0.1700

Data Index: 341204 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 3.1964. Min Range: -3.1964

Max Act: 2.9756. Min Act: -0.1700

Data Index: 439459 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 3.1964. Min Range: -3.1964

Max Act: 2.9756. Min Act: -0.1700

Data Index: 283265 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 3.1964. Min Range: -3.1964

Max Act: 2.9756. Min Act: -0.1700

Data Index: 349116 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 3.1964. Min Range: -3.1964

Max Act: 2.9756. Min Act: -0.1700

Data Index: 880952 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 3.1964. Min Range: -3.1964

Max Act: 2.9756. Min Act: -0.1700

Data Index: 1196113 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 3.1964. Min Range: -3.1964

Max Act: 2.9439. Min Act: -0.1700

Data Index: 939123 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 3.1964. Min Range: -3.1964

Max Act: 2.9439. Min Act: -0.1700

Data Index: 232177 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 3.1964. Min Range: -3.1964

Max Act: 2.9598. Min Act: -0.1700

Data Index: 291898 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 3.1964. Min Range: -3.1964

Max Act: 2.9439. Min Act: -0.1700

Data Index: 907930 (C4 (Web Text))

Max Activating Token Index: 744