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

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

Neuron 814 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: 3.4347. Min Range: -3.4347

Max Act: 3.4347. Min Act: -0.1700

Data Index: 694416 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 3.4347. Min Range: -3.4347

Max Act: 3.4190. Min Act: -0.1700

Data Index: 810561 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 3.4347. Min Range: -3.4347

Max Act: 3.2464. Min Act: -0.1700

Data Index: 54678 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 3.4347. Min Range: -3.4347

Max Act: 3.2149. Min Act: -0.1700

Data Index: 1315266 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 3.4347. Min Range: -3.4347

Max Act: 3.1677. Min Act: -0.1700

Data Index: 656645 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 3.4347. Min Range: -3.4347

Max Act: 3.1204. Min Act: -0.1700

Data Index: 359497 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 3.4347. Min Range: -3.4347

Max Act: 3.1047. Min Act: -0.1700

Data Index: 134650 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 3.4347. Min Range: -3.4347

Max Act: 3.0889. Min Act: -0.1700

Data Index: 982674 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 3.4347. Min Range: -3.4347

Max Act: 3.0574. Min Act: -0.1700

Data Index: 968838 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 3.4347. Min Range: -3.4347

Max Act: 3.0574. Min Act: -0.1700

Data Index: 1294055 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 3.4347. Min Range: -3.4347

Max Act: 3.0574. Min Act: -0.1700

Data Index: 167028 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 3.4347. Min Range: -3.4347

Max Act: 3.0416. Min Act: -0.1700

Data Index: 1354908 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 3.4347. Min Range: -3.4347

Max Act: 3.0258. Min Act: -0.1700

Data Index: 1173825 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 3.4347. Min Range: -3.4347

Max Act: 3.0100. Min Act: -0.1700

Data Index: 1176237 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 3.4347. Min Range: -3.4347

Max Act: 2.9942. Min Act: -0.1700

Data Index: 236097 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 3.4347. Min Range: -3.4347

Max Act: 2.9942. Min Act: -0.1700

Data Index: 181089 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 3.4347. Min Range: -3.4347

Max Act: 2.9942. Min Act: -0.1700

Data Index: 849476 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 3.4347. Min Range: -3.4347

Max Act: 2.9784. Min Act: -0.1700

Data Index: 448608 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 3.4347. Min Range: -3.4347

Max Act: 2.9942. Min Act: -0.1700

Data Index: 87195 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 3.4347. Min Range: -3.4347

Max Act: 2.9625. Min Act: -0.1700

Data Index: 112163 (C4 (Web Text))

Max Activating Token Index: 49