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

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

Neuron 401 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: 3.3961. Min Range: -3.3961

Max Act: 3.3961. Min Act: -0.1700

Data Index: 932583 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.3333. Min Act: -0.1700

Data Index: 930708 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.3333. Min Act: -0.1700

Data Index: 834688 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.2862. Min Act: -0.1700

Data Index: 806656 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.2705. Min Act: -0.1700

Data Index: 521943 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.2705. Min Act: -0.1700

Data Index: 795327 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.2548. Min Act: -0.1700

Data Index: 957560 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.2233. Min Act: -0.1700

Data Index: 1261715 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.2076. Min Act: -0.1700

Data Index: 917662 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.2076. Min Act: -0.1700

Data Index: 636517 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.2076. Min Act: -0.1700

Data Index: 875153 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.2233. Min Act: -0.1700

Data Index: 771735 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.2076. Min Act: -0.1700

Data Index: 677245 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.2076. Min Act: -0.1700

Data Index: 365019 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.2076. Min Act: -0.1700

Data Index: 699854 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.1918. Min Act: -0.1700

Data Index: 755036 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.1761. Min Act: -0.1700

Data Index: 438115 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.1918. Min Act: -0.1700

Data Index: 828466 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.1918. Min Act: -0.1700

Data Index: 816556 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.1918. Min Act: -0.1700

Data Index: 383560 (C4 (Web Text))

Max Activating Token Index: 290