Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 190 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.6610. Min Act: -0.1700

Data Index: 443089 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.6465. Min Act: -0.1700

Data Index: 832077 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.6235. Min Act: -0.1700

Data Index: 570551 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.5912. Min Act: -0.1700

Data Index: 1043735 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.6713. Min Act: -0.1700

Data Index: 58203 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.6754. Min Act: -0.1700

Data Index: 1009746 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.6752. Min Act: -0.1700

Data Index: 637688 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.6027. Min Act: -0.1700

Data Index: 285473 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.6372. Min Act: -0.1700

Data Index: 106166 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.5932. Min Act: -0.1700

Data Index: 628179 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.6340. Min Act: -0.1700

Data Index: 25936 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.5949. Min Act: -0.1700

Data Index: 1284721 (C4 (Web Text))

Max Activating Token Index: 425

Text #12

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.5580. Min Act: -0.1700

Data Index: 177892 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.5612. Min Act: -0.1700

Data Index: 811341 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.5924. Min Act: -0.1700

Data Index: 979878 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.6100. Min Act: -0.1700

Data Index: 25674 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.6118. Min Act: -0.1700

Data Index: 767959 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.5111. Min Act: -0.1700

Data Index: 1326033 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.5892. Min Act: -0.1700

Data Index: 1341576 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 3.6754. Min Range: -3.6754

Max Act: 3.5979. Min Act: -0.1700

Data Index: 1351476 (C4 (Web Text))

Max Activating Token Index: 701