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

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

Neuron 198 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: 5.8784. Min Range: -5.8784

Max Act: 5.8784. Min Act: -0.1650

Data Index: 830381 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.6909. Min Act: -0.1700

Data Index: 312304 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.6909. Min Act: -0.1700

Data Index: 326744 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.6597. Min Act: -0.1700

Data Index: 1029788 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.6284. Min Act: -0.1700

Data Index: 900371 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.6284. Min Act: -0.1700

Data Index: 232607 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.5972. Min Act: -0.1700

Data Index: 68027 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.6284. Min Act: -0.1700

Data Index: 736356 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.5972. Min Act: -0.1700

Data Index: 600638 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.6284. Min Act: -0.1700

Data Index: 234473 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.5659. Min Act: -0.1700

Data Index: 18597 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.5659. Min Act: -0.1700

Data Index: 862750 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.5034. Min Act: -0.1700

Data Index: 122478 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.5347. Min Act: -0.1700

Data Index: 257851 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.5347. Min Act: -0.1700

Data Index: 562918 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.5347. Min Act: -0.1700

Data Index: 538987 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.5034. Min Act: -0.1699

Data Index: 749138 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.4722. Min Act: -0.1700

Data Index: 328611 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.5347. Min Act: -0.1700

Data Index: 19161 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 5.8784. Min Range: -5.8784

Max Act: 5.4722. Min Act: -0.1700

Data Index: 304469 (C4 (Web Text))

Max Activating Token Index: 696