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

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

Neuron 764 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: 3.9818. Min Range: -3.9818

Max Act: 3.9818. Min Act: -0.1700

Data Index: 840263 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 3.9818. Min Range: -3.9818

Max Act: 3.9505. Min Act: -0.1700

Data Index: 304651 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 3.9818. Min Range: -3.9818

Max Act: 3.9505. Min Act: -0.1700

Data Index: 1328673 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 3.9818. Min Range: -3.9818

Max Act: 3.9505. Min Act: -0.1700

Data Index: 227715 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 3.9818. Min Range: -3.9818

Max Act: 3.9192. Min Act: -0.1700

Data Index: 984062 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 3.9818. Min Range: -3.9818

Max Act: 3.8879. Min Act: -0.1700

Data Index: 1052232 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 3.9818. Min Range: -3.9818

Max Act: 3.9192. Min Act: -0.1700

Data Index: 1224604 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 3.9818. Min Range: -3.9818

Max Act: 3.8567. Min Act: -0.1700

Data Index: 1280320 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 3.9818. Min Range: -3.9818

Max Act: 3.9192. Min Act: -0.1700

Data Index: 1350849 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 3.9818. Min Range: -3.9818

Max Act: 3.9192. Min Act: -0.1700

Data Index: 166450 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 3.9818. Min Range: -3.9818

Max Act: 3.8567. Min Act: -0.1700

Data Index: 524242 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 3.9818. Min Range: -3.9818

Max Act: 3.8567. Min Act: -0.1700

Data Index: 529930 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 3.9818. Min Range: -3.9818

Max Act: 3.8879. Min Act: -0.1700

Data Index: 434075 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 3.9818. Min Range: -3.9818

Max Act: 3.8879. Min Act: -0.1700

Data Index: 683259 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 3.9818. Min Range: -3.9818

Max Act: 3.8567. Min Act: -0.1700

Data Index: 1343773 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 3.9818. Min Range: -3.9818

Max Act: 3.8879. Min Act: -0.1700

Data Index: 780909 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 3.9818. Min Range: -3.9818

Max Act: 3.8879. Min Act: -0.1700

Data Index: 830006 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 3.9818. Min Range: -3.9818

Max Act: 3.8567. Min Act: -0.1700

Data Index: 824721 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 3.9818. Min Range: -3.9818

Max Act: 3.8254. Min Act: -0.1700

Data Index: 14484 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 3.9818. Min Range: -3.9818

Max Act: 3.8879. Min Act: -0.1700

Data Index: 173568 (C4 (Web Text))

Max Activating Token Index: 477