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

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

Neuron 98 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: 5.3863. Min Range: -5.3863

Max Act: 5.3863. Min Act: -0.1700

Data Index: 780250 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 5.3863. Min Range: -5.3863

Max Act: 5.3238. Min Act: -0.1700

Data Index: 931864 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 5.3863. Min Range: -5.3863

Max Act: 5.3238. Min Act: -0.1700

Data Index: 827879 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 5.3863. Min Range: -5.3863

Max Act: 5.1988. Min Act: -0.1700

Data Index: 348954 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 5.3863. Min Range: -5.3863

Max Act: 5.2613. Min Act: -0.1700

Data Index: 893367 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 5.3863. Min Range: -5.3863

Max Act: 5.2300. Min Act: -0.1700

Data Index: 1061165 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 5.3863. Min Range: -5.3863

Max Act: 5.2300. Min Act: -0.1700

Data Index: 850502 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 5.3863. Min Range: -5.3863

Max Act: 5.1363. Min Act: -0.1700

Data Index: 1219463 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 5.3863. Min Range: -5.3863

Max Act: 5.1050. Min Act: -0.1700

Data Index: 444103 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 5.3863. Min Range: -5.3863

Max Act: 5.1363. Min Act: -0.1700

Data Index: 451819 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 5.3863. Min Range: -5.3863

Max Act: 5.1050. Min Act: -0.1700

Data Index: 158771 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 5.3863. Min Range: -5.3863

Max Act: 5.0425. Min Act: -0.1700

Data Index: 883183 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 5.3863. Min Range: -5.3863

Max Act: 5.0738. Min Act: -0.1700

Data Index: 823159 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 5.3863. Min Range: -5.3863

Max Act: 5.0113. Min Act: -0.1700

Data Index: 1246416 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 5.3863. Min Range: -5.3863

Max Act: 5.0425. Min Act: -0.1700

Data Index: 587939 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 5.3863. Min Range: -5.3863

Max Act: 5.1050. Min Act: -0.1700

Data Index: 437796 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 5.3863. Min Range: -5.3863

Max Act: 5.0113. Min Act: -0.1700

Data Index: 329288 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 5.3863. Min Range: -5.3863

Max Act: 5.0425. Min Act: -0.1700

Data Index: 365392 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 5.3863. Min Range: -5.3863

Max Act: 4.9800. Min Act: -0.1700

Data Index: 568912 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 5.3863. Min Range: -5.3863

Max Act: 5.0425. Min Act: -0.1700

Data Index: 1199449 (C4 (Web Text))

Max Activating Token Index: 945