Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 368 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.3530. Min Range: -3.3530

Max Act: 3.3530. Min Act: -0.1700

Data Index: 1262850 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 3.3530. Min Range: -3.3530

Max Act: 3.1486. Min Act: -0.1700

Data Index: 957025 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 3.3530. Min Range: -3.3530

Max Act: 3.1171. Min Act: -0.1700

Data Index: 389048 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 3.3530. Min Range: -3.3530

Max Act: 3.1013. Min Act: -0.1700

Data Index: 1280666 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 3.3530. Min Range: -3.3530

Max Act: 3.0856. Min Act: -0.1700

Data Index: 976847 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 3.3530. Min Range: -3.3530

Max Act: 3.0540. Min Act: -0.1700

Data Index: 510769 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 3.3530. Min Range: -3.3530

Max Act: 3.0540. Min Act: -0.1700

Data Index: 368288 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 3.3530. Min Range: -3.3530

Max Act: 3.0698. Min Act: -0.1700

Data Index: 887497 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 3.3530. Min Range: -3.3530

Max Act: 3.0698. Min Act: -0.1700

Data Index: 822802 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 3.3530. Min Range: -3.3530

Max Act: 3.0382. Min Act: -0.1700

Data Index: 246229 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 3.3530. Min Range: -3.3530

Max Act: 3.0382. Min Act: -0.1700

Data Index: 1170136 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 3.3530. Min Range: -3.3530

Max Act: 3.0540. Min Act: -0.1700

Data Index: 785848 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 3.3530. Min Range: -3.3530

Max Act: 3.0224. Min Act: -0.1700

Data Index: 808603 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 3.3530. Min Range: -3.3530

Max Act: 3.0382. Min Act: -0.1700

Data Index: 1096268 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.9908. Min Act: -0.1700

Data Index: 289428 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 3.3530. Min Range: -3.3530

Max Act: 3.0224. Min Act: -0.1700

Data Index: 1046048 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.9908. Min Act: -0.1700

Data Index: 1047982 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.9908. Min Act: -0.1700

Data Index: 832730 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.9908. Min Act: -0.1700

Data Index: 394421 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 3.3530. Min Range: -3.3530

Max Act: 2.9908. Min Act: -0.1700

Data Index: 423953 (C4 (Web Text))

Max Activating Token Index: 313