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

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

Neuron 1763 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.9692. Min Act: -0.1700

Data Index: 1610031 (Python Code)

Max Activating Token Index: 363

Text #1

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.9223. Min Act: -0.1700

Data Index: 1340652 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.8754. Min Act: -0.1700

Data Index: 1372004 (Python Code)

Max Activating Token Index: 198

Text #3

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.8597. Min Act: -0.1700

Data Index: 693618 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.8597. Min Act: -0.1700

Data Index: 587635 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.8754. Min Act: -0.1700

Data Index: 1504164 (Python Code)

Max Activating Token Index: 544

Text #6

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.8128. Min Act: -0.1700

Data Index: 1301239 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.7972. Min Act: -0.1700

Data Index: 1319235 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.9066. Min Act: -0.1700

Data Index: 250297 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.8441. Min Act: -0.1700

Data Index: 475802 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.8441. Min Act: -0.1700

Data Index: 520641 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.8597. Min Act: -0.1700

Data Index: 897860 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.8128. Min Act: -0.1700

Data Index: 1101245 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.8441. Min Act: -0.1700

Data Index: 369664 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.8284. Min Act: -0.1700

Data Index: 708839 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.9066. Min Act: -0.1700

Data Index: 426645 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.7815. Min Act: -0.1700

Data Index: 45200 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.7972. Min Act: -0.1700

Data Index: 919025 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.7659. Min Act: -0.1700

Data Index: 982822 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 3.9692. Min Range: -3.9692

Max Act: 3.7972. Min Act: -0.1700

Data Index: 1342793 (C4 (Web Text))

Max Activating Token Index: 297