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

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

Neuron 164 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: 3.5001. Min Range: -3.5001

Max Act: 3.5001. Min Act: -0.1700

Data Index: 859385 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.4687. Min Act: -0.1700

Data Index: 138774 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.4374. Min Act: -0.1700

Data Index: 219935 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.4217. Min Act: -0.1700

Data Index: 132305 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.4060. Min Act: -0.1700

Data Index: 1049916 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3903. Min Act: -0.1700

Data Index: 36138 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3746. Min Act: -0.1700

Data Index: 109993 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3903. Min Act: -0.1700

Data Index: 995329 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3746. Min Act: -0.1700

Data Index: 446886 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3903. Min Act: -0.1700

Data Index: 285072 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3746. Min Act: -0.1700

Data Index: 178516 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3746. Min Act: -0.1700

Data Index: 1286477 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3746. Min Act: -0.1700

Data Index: 506404 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3589. Min Act: -0.1700

Data Index: 1085557 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3589. Min Act: -0.1700

Data Index: 1066900 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3433. Min Act: -0.1700

Data Index: 286695 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3589. Min Act: -0.1700

Data Index: 574660 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3903. Min Act: -0.1700

Data Index: 1266948 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3589. Min Act: -0.1700

Data Index: 1039797 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 3.5001. Min Range: -3.5001

Max Act: 3.3433. Min Act: -0.1700

Data Index: 1164904 (C4 (Web Text))

Max Activating Token Index: 39