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

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

Neuron 1092 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: 5.4874. Min Range: -5.4874

Max Act: 5.4874. Min Act: -0.1700

Data Index: 420334 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 5.4874. Min Range: -5.4874

Max Act: 5.3936. Min Act: -0.1700

Data Index: 97138 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 5.4874. Min Range: -5.4874

Max Act: 5.3936. Min Act: -0.1700

Data Index: 236864 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 5.4874. Min Range: -5.4874

Max Act: 5.3936. Min Act: -0.1700

Data Index: 1094312 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 5.4874. Min Range: -5.4874

Max Act: 5.4249. Min Act: -0.1700

Data Index: 592149 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 5.4874. Min Range: -5.4874

Max Act: 5.3936. Min Act: -0.1700

Data Index: 871008 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 5.4874. Min Range: -5.4874

Max Act: 5.3624. Min Act: -0.1700

Data Index: 565577 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 5.4874. Min Range: -5.4874

Max Act: 5.2686. Min Act: -0.1700

Data Index: 1040280 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 5.4874. Min Range: -5.4874

Max Act: 5.2999. Min Act: -0.1700

Data Index: 13854 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 5.4874. Min Range: -5.4874

Max Act: 5.2686. Min Act: -0.1700

Data Index: 374221 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 5.4874. Min Range: -5.4874

Max Act: 5.1749. Min Act: -0.1700

Data Index: 273295 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 5.4874. Min Range: -5.4874

Max Act: 5.2061. Min Act: -0.1700

Data Index: 1279408 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 5.4874. Min Range: -5.4874

Max Act: 5.2061. Min Act: -0.1700

Data Index: 352111 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 5.4874. Min Range: -5.4874

Max Act: 5.2374. Min Act: -0.1700

Data Index: 289553 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 5.4874. Min Range: -5.4874

Max Act: 5.2686. Min Act: -0.1700

Data Index: 1041913 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 5.4874. Min Range: -5.4874

Max Act: 5.1749. Min Act: -0.1700

Data Index: 885615 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 5.4874. Min Range: -5.4874

Max Act: 5.1436. Min Act: -0.1700

Data Index: 742622 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 5.4874. Min Range: -5.4874

Max Act: 5.1124. Min Act: -0.1700

Data Index: 476392 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 5.4874. Min Range: -5.4874

Max Act: 5.1436. Min Act: -0.1700

Data Index: 83804 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 5.4874. Min Range: -5.4874

Max Act: 5.1436. Min Act: -0.1700

Data Index: 621146 (C4 (Web Text))

Max Activating Token Index: 65