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

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

Neuron 1725 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.2959. Min Act: -0.1700

Data Index: 874854 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.2015. Min Act: -0.1700

Data Index: 640122 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.2173. Min Act: -0.1700

Data Index: 1132686 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.1701. Min Act: -0.1700

Data Index: 614856 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.1543. Min Act: -0.1700

Data Index: 249512 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.1386. Min Act: -0.1700

Data Index: 1201683 (C4 (Web Text))

Max Activating Token Index: 763

Text #6

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.1228. Min Act: -0.1700

Data Index: 544705 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.1071. Min Act: -0.1700

Data Index: 991953 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.1071. Min Act: -0.1700

Data Index: 638659 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.1228. Min Act: -0.1700

Data Index: 520000 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.1071. Min Act: -0.1700

Data Index: 673181 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.0913. Min Act: -0.1700

Data Index: 5591 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.0913. Min Act: -0.1700

Data Index: 11753 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.0755. Min Act: -0.1700

Data Index: 226481 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.0913. Min Act: -0.1700

Data Index: 1057429 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.1071. Min Act: -0.1700

Data Index: 1064498 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.0913. Min Act: -0.1700

Data Index: 1266468 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.0755. Min Act: -0.1700

Data Index: 253016 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.0755. Min Act: -0.1700

Data Index: 185315 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 3.2959. Min Range: -3.2959

Max Act: 3.0913. Min Act: -0.1700

Data Index: 311562 (C4 (Web Text))

Max Activating Token Index: 907