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

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

Neuron 1456 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: 5.3487. Min Range: -5.3487

Max Act: 5.3487. Min Act: -0.1700

Data Index: 131503 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 5.3487. Min Range: -5.3487

Max Act: 5.2549. Min Act: -0.1700

Data Index: 56060 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 5.3487. Min Range: -5.3487

Max Act: 5.3487. Min Act: -0.1700

Data Index: 374124 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 5.3487. Min Range: -5.3487

Max Act: 5.2862. Min Act: -0.1700

Data Index: 61086 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 5.3487. Min Range: -5.3487

Max Act: 5.2237. Min Act: -0.1700

Data Index: 51011 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 5.3487. Min Range: -5.3487

Max Act: 5.2237. Min Act: -0.1700

Data Index: 1145443 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 5.3487. Min Range: -5.3487

Max Act: 5.2549. Min Act: -0.1700

Data Index: 1166857 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 5.3487. Min Range: -5.3487

Max Act: 5.2862. Min Act: -0.1700

Data Index: 700026 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 5.3487. Min Range: -5.3487

Max Act: 5.2862. Min Act: -0.1700

Data Index: 295253 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 5.3487. Min Range: -5.3487

Max Act: 5.1924. Min Act: -0.1700

Data Index: 607327 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 5.3487. Min Range: -5.3487

Max Act: 5.2549. Min Act: -0.1700

Data Index: 1165631 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 5.3487. Min Range: -5.3487

Max Act: 5.1924. Min Act: -0.1700

Data Index: 1005690 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 5.3487. Min Range: -5.3487

Max Act: 5.2549. Min Act: -0.1700

Data Index: 290107 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 5.3487. Min Range: -5.3487

Max Act: 5.1299. Min Act: -0.1700

Data Index: 696407 (C4 (Web Text))

Max Activating Token Index: 747

Text #14

Max Range: 5.3487. Min Range: -5.3487

Max Act: 5.1299. Min Act: -0.1700

Data Index: 251693 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 5.3487. Min Range: -5.3487

Max Act: 5.1612. Min Act: -0.1700

Data Index: 11180 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 5.3487. Min Range: -5.3487

Max Act: 5.1924. Min Act: -0.1700

Data Index: 325399 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 5.3487. Min Range: -5.3487

Max Act: 5.1924. Min Act: -0.1700

Data Index: 1035897 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 5.3487. Min Range: -5.3487

Max Act: 5.0987. Min Act: -0.1700

Data Index: 840147 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 5.3487. Min Range: -5.3487

Max Act: 5.1612. Min Act: -0.1700

Data Index: 1357847 (C4 (Web Text))

Max Activating Token Index: 490