Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 221 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.5490. Min Act: -0.1700

Data Index: 1252727 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.4865. Min Act: -0.1700

Data Index: 1075740 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.3615. Min Act: -0.1700

Data Index: 1216747 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.3615. Min Act: -0.1700

Data Index: 718897 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.3927. Min Act: -0.1700

Data Index: 254103 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.2990. Min Act: -0.1700

Data Index: 291415 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.2365. Min Act: -0.1700

Data Index: 601198 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.2990. Min Act: -0.1700

Data Index: 444591 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.2365. Min Act: -0.1700

Data Index: 270288 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.2990. Min Act: -0.1700

Data Index: 477583 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.2365. Min Act: -0.1700

Data Index: 207121 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.1740. Min Act: -0.1700

Data Index: 1354119 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.2365. Min Act: -0.1700

Data Index: 821699 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.1115. Min Act: -0.1700

Data Index: 976160 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.1115. Min Act: -0.1700

Data Index: 63621 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.1115. Min Act: -0.1700

Data Index: 1105761 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.0490. Min Act: -0.1700

Data Index: 199242 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.0802. Min Act: -0.1700

Data Index: 1046186 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.1427. Min Act: -0.1700

Data Index: 796127 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 5.5490. Min Range: -5.5490

Max Act: 5.0802. Min Act: -0.1700

Data Index: 1232278 (C4 (Web Text))

Max Activating Token Index: 69