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

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

Neuron 1966 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.6128. Min Act: -0.1700

Data Index: 1112865 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.4253. Min Act: -0.1700

Data Index: 633163 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.2847. Min Act: -0.1700

Data Index: 1092025 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.2847. Min Act: -0.1700

Data Index: 222099 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.2691. Min Act: -0.1700

Data Index: 700387 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.3003. Min Act: -0.1700

Data Index: 43515 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.3003. Min Act: -0.1700

Data Index: 806880 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.2847. Min Act: -0.1700

Data Index: 40079 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.2847. Min Act: -0.1700

Data Index: 20213 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.2847. Min Act: -0.1700

Data Index: 1234939 (C4 (Web Text))

Max Activating Token Index: 500

Text #10

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.2378. Min Act: -0.1700

Data Index: 927420 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.2222. Min Act: -0.1700

Data Index: 1181185 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.2222. Min Act: -0.1700

Data Index: 451131 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.1753. Min Act: -0.1700

Data Index: 113167 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.2222. Min Act: -0.1700

Data Index: 485156 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.1909. Min Act: -0.1700

Data Index: 1082973 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.2066. Min Act: -0.1700

Data Index: 175117 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.2222. Min Act: -0.1700

Data Index: 1133154 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.1753. Min Act: -0.1700

Data Index: 1210898 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 5.6128. Min Range: -5.6128

Max Act: 5.1597. Min Act: -0.1700

Data Index: 992136 (C4 (Web Text))

Max Activating Token Index: 630