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

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

Neuron 1910 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0708. Min Range: -4.0708

Max Act: 4.0708. Min Act: -0.1700

Data Index: 7520 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 4.0708. Min Range: -4.0708

Max Act: 3.9458. Min Act: -0.1700

Data Index: 865014 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 4.0708. Min Range: -4.0708

Max Act: 3.8207. Min Act: -0.1700

Data Index: 796377 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 4.0708. Min Range: -4.0708

Max Act: 3.7894. Min Act: -0.1700

Data Index: 149389 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 4.0708. Min Range: -4.0708

Max Act: 3.7894. Min Act: -0.1700

Data Index: 1242470 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 4.0708. Min Range: -4.0708

Max Act: 3.7894. Min Act: -0.1700

Data Index: 259111 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 4.0708. Min Range: -4.0708

Max Act: 3.7581. Min Act: -0.1700

Data Index: 124628 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 4.0708. Min Range: -4.0708

Max Act: 3.6955. Min Act: -0.1700

Data Index: 613087 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 4.0708. Min Range: -4.0708

Max Act: 3.7268. Min Act: -0.1700

Data Index: 837034 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 4.0708. Min Range: -4.0708

Max Act: 3.7268. Min Act: -0.1700

Data Index: 355225 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 4.0708. Min Range: -4.0708

Max Act: 3.7268. Min Act: -0.1700

Data Index: 707306 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 4.0708. Min Range: -4.0708

Max Act: 3.6955. Min Act: -0.1700

Data Index: 218731 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 4.0708. Min Range: -4.0708

Max Act: 3.6955. Min Act: -0.1700

Data Index: 636320 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 4.0708. Min Range: -4.0708

Max Act: 3.6955. Min Act: -0.1700

Data Index: 268730 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 4.0708. Min Range: -4.0708

Max Act: 3.6642. Min Act: -0.1700

Data Index: 199644 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 4.0708. Min Range: -4.0708

Max Act: 3.6642. Min Act: -0.1700

Data Index: 749433 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 4.0708. Min Range: -4.0708

Max Act: 3.6955. Min Act: -0.1700

Data Index: 218949 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 4.0708. Min Range: -4.0708

Max Act: 3.6955. Min Act: -0.1700

Data Index: 484973 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 4.0708. Min Range: -4.0708

Max Act: 3.6955. Min Act: -0.1700

Data Index: 285384 (C4 (Web Text))

Max Activating Token Index: 515

Text #19

Max Range: 4.0708. Min Range: -4.0708

Max Act: 3.6955. Min Act: -0.1700

Data Index: 920531 (C4 (Web Text))

Max Activating Token Index: 29