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

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

Neuron 1598 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.8025. Min Act: -0.1700

Data Index: 562545 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.7713. Min Act: -0.1700

Data Index: 791878 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.7400. Min Act: -0.1700

Data Index: 194165 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.6463. Min Act: -0.1699

Data Index: 1207312 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.6775. Min Act: -0.1700

Data Index: 270233 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.6150. Min Act: -0.1700

Data Index: 1160006 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.5525. Min Act: -0.1700

Data Index: 407391 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.6150. Min Act: -0.1700

Data Index: 300133 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.6463. Min Act: -0.1700

Data Index: 876923 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.5838. Min Act: -0.1700

Data Index: 80175 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.5838. Min Act: -0.1700

Data Index: 960618 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.5838. Min Act: -0.1700

Data Index: 879228 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.5525. Min Act: -0.1700

Data Index: 980137 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.5838. Min Act: -0.1700

Data Index: 688230 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.5213. Min Act: -0.1700

Data Index: 1076842 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.5838. Min Act: -0.1700

Data Index: 428486 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.5213. Min Act: -0.1700

Data Index: 931825 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.5525. Min Act: -0.1700

Data Index: 762863 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.5525. Min Act: -0.1700

Data Index: 671548 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 5.8025. Min Range: -5.8025

Max Act: 5.5213. Min Act: -0.1700

Data Index: 55929 (C4 (Web Text))

Max Activating Token Index: 662