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

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

Neuron 439 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: 3.6844. Min Range: -3.6844

Max Act: 3.6844. Min Act: -0.1700

Data Index: 801963 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5278. Min Act: -0.1700

Data Index: 185043 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5435. Min Act: -0.1700

Data Index: 51182 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.4965. Min Act: -0.1700

Data Index: 574191 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5121. Min Act: -0.1700

Data Index: 596447 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.4965. Min Act: -0.1700

Data Index: 1320705 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.4651. Min Act: -0.1700

Data Index: 1224248 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5121. Min Act: -0.1700

Data Index: 780344 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5278. Min Act: -0.1700

Data Index: 1187215 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.4965. Min Act: -0.1700

Data Index: 354780 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5121. Min Act: -0.1700

Data Index: 1140547 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.4494. Min Act: -0.1700

Data Index: 1279310 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.4338. Min Act: -0.1700

Data Index: 993787 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.4338. Min Act: -0.1700

Data Index: 146118 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.4808. Min Act: -0.1700

Data Index: 634097 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.4651. Min Act: -0.1700

Data Index: 1331989 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.4024. Min Act: -0.1700

Data Index: 1060210 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.4494. Min Act: -0.1700

Data Index: 950975 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.4181. Min Act: -0.1700

Data Index: 750008 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.4651. Min Act: -0.1700

Data Index: 602392 (C4 (Web Text))

Max Activating Token Index: 61