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

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

Neuron 1390 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.6913. Min Act: -0.1700

Data Index: 777103 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.6130. Min Act: -0.1700

Data Index: 1269178 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.6756. Min Act: -0.1700

Data Index: 1298650 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.6443. Min Act: -0.1700

Data Index: 73039 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.6287. Min Act: -0.1700

Data Index: 1334334 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.5661. Min Act: -0.1700

Data Index: 162983 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.5817. Min Act: -0.1700

Data Index: 1264955 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.6287. Min Act: -0.1700

Data Index: 851087 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.5661. Min Act: -0.1700

Data Index: 965606 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.5661. Min Act: -0.1700

Data Index: 408816 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.5661. Min Act: -0.1700

Data Index: 1062862 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.5661. Min Act: -0.1700

Data Index: 497657 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.5504. Min Act: -0.1700

Data Index: 494626 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.5504. Min Act: -0.1700

Data Index: 900809 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.5504. Min Act: -0.1700

Data Index: 1116005 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.5347. Min Act: -0.1700

Data Index: 984139 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.5504. Min Act: -0.1700

Data Index: 251527 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.5347. Min Act: -0.1700

Data Index: 1273171 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.5347. Min Act: -0.1700

Data Index: 950979 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.5191. Min Act: -0.1700

Data Index: 65003 (C4 (Web Text))

Max Activating Token Index: 341