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

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

Neuron 336 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: 3.8471. Min Range: -3.8471

Max Act: 3.8471. Min Act: -0.1700

Data Index: 1133908 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 3.8471. Min Range: -3.8471

Max Act: 3.7220. Min Act: -0.1700

Data Index: 530782 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 3.8471. Min Range: -3.8471

Max Act: 3.7532. Min Act: -0.1700

Data Index: 1009610 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 3.8471. Min Range: -3.8471

Max Act: 3.8158. Min Act: -0.1700

Data Index: 137760 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 3.8471. Min Range: -3.8471

Max Act: 3.6281. Min Act: -0.1700

Data Index: 226359 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 3.8471. Min Range: -3.8471

Max Act: 3.6281. Min Act: -0.1700

Data Index: 511177 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 3.8471. Min Range: -3.8471

Max Act: 3.6281. Min Act: -0.1700

Data Index: 483331 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 3.8471. Min Range: -3.8471

Max Act: 3.5811. Min Act: -0.1700

Data Index: 1345597 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 3.8471. Min Range: -3.8471

Max Act: 3.6281. Min Act: -0.1700

Data Index: 488393 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 3.8471. Min Range: -3.8471

Max Act: 3.6594. Min Act: -0.1700

Data Index: 1161975 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 3.8471. Min Range: -3.8471

Max Act: 3.5654. Min Act: -0.1700

Data Index: 1119370 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 3.8471. Min Range: -3.8471

Max Act: 3.6907. Min Act: -0.1700

Data Index: 693033 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 3.8471. Min Range: -3.8471

Max Act: 3.5967. Min Act: -0.1700

Data Index: 300718 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 3.8471. Min Range: -3.8471

Max Act: 3.5967. Min Act: -0.1700

Data Index: 501173 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 3.8471. Min Range: -3.8471

Max Act: 3.5811. Min Act: -0.1700

Data Index: 229719 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 3.8471. Min Range: -3.8471

Max Act: 3.5654. Min Act: -0.1700

Data Index: 369313 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 3.8471. Min Range: -3.8471

Max Act: 3.5967. Min Act: -0.1700

Data Index: 594230 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 3.8471. Min Range: -3.8471

Max Act: 3.5341. Min Act: -0.1700

Data Index: 834088 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 3.8471. Min Range: -3.8471

Max Act: 3.5654. Min Act: -0.1700

Data Index: 225258 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 3.8471. Min Range: -3.8471

Max Act: 3.6281. Min Act: -0.1700

Data Index: 712980 (C4 (Web Text))

Max Activating Token Index: 536