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

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

Neuron 1633 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: 3.2167. Min Range: -3.2167

Max Act: 3.2167. Min Act: -0.1700

Data Index: 667123 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.1852. Min Act: -0.1700

Data Index: 1179818 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.2009. Min Act: -0.1700

Data Index: 41215 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.2009. Min Act: -0.1700

Data Index: 1223652 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.2009. Min Act: -0.1700

Data Index: 629561 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.1695. Min Act: -0.1700

Data Index: 440501 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.1852. Min Act: -0.1700

Data Index: 1153768 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.1852. Min Act: -0.1700

Data Index: 169555 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.1852. Min Act: -0.1700

Data Index: 909001 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.1537. Min Act: -0.1700

Data Index: 432964 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.1695. Min Act: -0.1700

Data Index: 49225 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.1380. Min Act: -0.1700

Data Index: 480775 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.1222. Min Act: -0.1700

Data Index: 570155 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.1380. Min Act: -0.1700

Data Index: 1230440 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.1380. Min Act: -0.1700

Data Index: 795958 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.1222. Min Act: -0.1700

Data Index: 1285475 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.1222. Min Act: -0.1700

Data Index: 1050108 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.1380. Min Act: -0.1700

Data Index: 722792 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.1380. Min Act: -0.1700

Data Index: 445849 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 3.2167. Min Range: -3.2167

Max Act: 3.1222. Min Act: -0.1700

Data Index: 321284 (C4 (Web Text))

Max Activating Token Index: 31