Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1332 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.1028. Min Range: -5.1028

Max Act: 5.1028. Min Act: -0.1700

Data Index: 231378 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 5.1028. Min Range: -5.1028

Max Act: 5.0090. Min Act: -0.1700

Data Index: 428091 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 5.1028. Min Range: -5.1028

Max Act: 5.0090. Min Act: -0.1700

Data Index: 1159439 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 5.1028. Min Range: -5.1028

Max Act: 4.9778. Min Act: -0.1700

Data Index: 474263 (C4 (Web Text))

Max Activating Token Index: 184

Text #4

Max Range: 5.1028. Min Range: -5.1028

Max Act: 4.8840. Min Act: -0.1700

Data Index: 778284 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 5.1028. Min Range: -5.1028

Max Act: 4.8215. Min Act: -0.1700

Data Index: 559077 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 5.1028. Min Range: -5.1028

Max Act: 4.8215. Min Act: -0.1700

Data Index: 211824 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 5.1028. Min Range: -5.1028

Max Act: 4.8215. Min Act: -0.1700

Data Index: 15208 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 5.1028. Min Range: -5.1028

Max Act: 4.7903. Min Act: -0.1700

Data Index: 78161 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 5.1028. Min Range: -5.1028

Max Act: 4.8215. Min Act: -0.1700

Data Index: 916876 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 5.1028. Min Range: -5.1028

Max Act: 4.7903. Min Act: -0.1700

Data Index: 214606 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 5.1028. Min Range: -5.1028

Max Act: 4.8215. Min Act: -0.1700

Data Index: 1082184 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 5.1028. Min Range: -5.1028

Max Act: 4.7903. Min Act: -0.1700

Data Index: 1106311 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 5.1028. Min Range: -5.1028

Max Act: 4.7590. Min Act: -0.1700

Data Index: 36405 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 5.1028. Min Range: -5.1028

Max Act: 4.7590. Min Act: -0.1700

Data Index: 1170352 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 5.1028. Min Range: -5.1028

Max Act: 4.7590. Min Act: -0.1700

Data Index: 195595 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 5.1028. Min Range: -5.1028

Max Act: 4.7590. Min Act: -0.1700

Data Index: 1045726 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 5.1028. Min Range: -5.1028

Max Act: 4.6965. Min Act: -0.1700

Data Index: 673677 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 5.1028. Min Range: -5.1028

Max Act: 4.7278. Min Act: -0.1700

Data Index: 724120 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 5.1028. Min Range: -5.1028

Max Act: 4.7278. Min Act: -0.1700

Data Index: 1007997 (C4 (Web Text))

Max Activating Token Index: 264