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

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

Neuron 1072 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.5361. Min Act: -0.1700

Data Index: 182089 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.3636. Min Act: -0.1698

Data Index: 712994 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.3636. Min Act: -0.1700

Data Index: 653222 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.3008. Min Act: -0.1700

Data Index: 660222 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.3165. Min Act: -0.1700

Data Index: 9053 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.2694. Min Act: -0.1700

Data Index: 399073 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.2694. Min Act: -0.1700

Data Index: 683577 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.2537. Min Act: -0.1700

Data Index: 796177 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.2537. Min Act: -0.1700

Data Index: 500109 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.2537. Min Act: -0.1700

Data Index: 582505 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.2537. Min Act: -0.1700

Data Index: 1270416 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.1908. Min Act: -0.1700

Data Index: 963112 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.1593. Min Act: -0.1698

Data Index: 503064 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.1593. Min Act: -0.1700

Data Index: 373578 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.1593. Min Act: -0.1700

Data Index: 717111 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.2065. Min Act: -0.1700

Data Index: 743442 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.1908. Min Act: -0.1700

Data Index: 1190924 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.1750. Min Act: -0.1700

Data Index: 1049937 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.1436. Min Act: -0.1700

Data Index: 575365 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.1750. Min Act: -0.1700

Data Index: 708187 (C4 (Web Text))

Max Activating Token Index: 22