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

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

Neuron 1940 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: 3.3083. Min Range: -3.3083

Max Act: 3.3083. Min Act: -0.1700

Data Index: 312774 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.3083. Min Act: -0.1700

Data Index: 151029 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.2140. Min Act: -0.1700

Data Index: 558526 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.1825. Min Act: -0.1700

Data Index: 290253 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.1195. Min Act: -0.1700

Data Index: 762065 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.0880. Min Act: -0.1700

Data Index: 828591 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.0880. Min Act: -0.1700

Data Index: 289058 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.0880. Min Act: -0.1700

Data Index: 687465 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.0880. Min Act: -0.1700

Data Index: 6747 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.1195. Min Act: -0.1700

Data Index: 486964 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.0880. Min Act: -0.1700

Data Index: 953932 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.0880. Min Act: -0.1700

Data Index: 982739 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.0564. Min Act: -0.1700

Data Index: 899964 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.0564. Min Act: -0.1700

Data Index: 202402 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.0249. Min Act: -0.1700

Data Index: 275575 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.0880. Min Act: -0.1700

Data Index: 181682 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.0564. Min Act: -0.1700

Data Index: 580799 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.0564. Min Act: -0.1700

Data Index: 470305 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.0564. Min Act: -0.1700

Data Index: 50159 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 3.3083. Min Range: -3.3083

Max Act: 3.0564. Min Act: -0.1700

Data Index: 369674 (C4 (Web Text))

Max Activating Token Index: 775