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

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

Neuron 985 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2149. Min Range: -3.2149

Max Act: 3.2149. Min Act: -0.1700

Data Index: 184894 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 3.2149. Min Range: -3.2149

Max Act: 3.1992. Min Act: -0.1700

Data Index: 752039 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 3.2149. Min Range: -3.2149

Max Act: 3.1520. Min Act: -0.1700

Data Index: 216421 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 3.2149. Min Range: -3.2149

Max Act: 3.0889. Min Act: -0.1700

Data Index: 542836 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 3.2149. Min Range: -3.2149

Max Act: 3.0889. Min Act: -0.1700

Data Index: 986734 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 3.2149. Min Range: -3.2149

Max Act: 3.0889. Min Act: -0.1700

Data Index: 145866 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 3.2149. Min Range: -3.2149

Max Act: 3.0731. Min Act: -0.1700

Data Index: 805188 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 3.2149. Min Range: -3.2149

Max Act: 3.0731. Min Act: -0.1700

Data Index: 149321 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 3.2149. Min Range: -3.2149

Max Act: 3.0574. Min Act: -0.1700

Data Index: 498454 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 3.2149. Min Range: -3.2149

Max Act: 3.0416. Min Act: -0.1700

Data Index: 939255 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 3.2149. Min Range: -3.2149

Max Act: 3.0416. Min Act: -0.1700

Data Index: 45926 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 3.2149. Min Range: -3.2149

Max Act: 3.0100. Min Act: -0.1700

Data Index: 1154690 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 3.2149. Min Range: -3.2149

Max Act: 2.9942. Min Act: -0.1700

Data Index: 1207155 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 3.2149. Min Range: -3.2149

Max Act: 2.9942. Min Act: -0.1700

Data Index: 826430 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 3.2149. Min Range: -3.2149

Max Act: 2.9784. Min Act: -0.1700

Data Index: 601011 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 3.2149. Min Range: -3.2149

Max Act: 2.9784. Min Act: -0.1700

Data Index: 78462 (C4 (Web Text))

Max Activating Token Index: 538

Text #16

Max Range: 3.2149. Min Range: -3.2149

Max Act: 2.9784. Min Act: -0.1700

Data Index: 1049057 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 3.2149. Min Range: -3.2149

Max Act: 2.9625. Min Act: -0.1700

Data Index: 397028 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 3.2149. Min Range: -3.2149

Max Act: 2.9467. Min Act: -0.1700

Data Index: 208548 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 3.2149. Min Range: -3.2149

Max Act: 2.9467. Min Act: -0.1700

Data Index: 502901 (C4 (Web Text))

Max Activating Token Index: 51