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

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

Neuron 1241 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: 5.7238. Min Range: -5.7238

Max Act: 5.7238. Min Act: -0.1700

Data Index: 143187 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.7238. Min Range: -5.7238

Max Act: 5.5050. Min Act: -0.1700

Data Index: 668947 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.7238. Min Range: -5.7238

Max Act: 5.4738. Min Act: -0.1700

Data Index: 677384 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 5.7238. Min Range: -5.7238

Max Act: 5.4425. Min Act: -0.1700

Data Index: 1165443 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 5.7238. Min Range: -5.7238

Max Act: 5.3488. Min Act: -0.1699

Data Index: 1052850 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 5.7238. Min Range: -5.7238

Max Act: 5.3175. Min Act: -0.1700

Data Index: 308879 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 5.7238. Min Range: -5.7238

Max Act: 5.3488. Min Act: -0.1700

Data Index: 354557 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 5.7238. Min Range: -5.7238

Max Act: 5.2238. Min Act: -0.1700

Data Index: 57856 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 5.7238. Min Range: -5.7238

Max Act: 5.2550. Min Act: -0.1700

Data Index: 353187 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 5.7238. Min Range: -5.7238

Max Act: 5.1613. Min Act: -0.1700

Data Index: 1134291 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 5.7238. Min Range: -5.7238

Max Act: 5.1925. Min Act: -0.1700

Data Index: 1101474 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 5.7238. Min Range: -5.7238

Max Act: 5.1925. Min Act: -0.1700

Data Index: 1259225 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 5.7238. Min Range: -5.7238

Max Act: 5.1613. Min Act: -0.1700

Data Index: 302290 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 5.7238. Min Range: -5.7238

Max Act: 5.1925. Min Act: -0.1700

Data Index: 859850 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 5.7238. Min Range: -5.7238

Max Act: 5.1613. Min Act: -0.1700

Data Index: 518990 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 5.7238. Min Range: -5.7238

Max Act: 5.1613. Min Act: -0.1700

Data Index: 93211 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 5.7238. Min Range: -5.7238

Max Act: 5.1613. Min Act: -0.1700

Data Index: 189049 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 5.7238. Min Range: -5.7238

Max Act: 5.1300. Min Act: -0.1700

Data Index: 794421 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 5.7238. Min Range: -5.7238

Max Act: 5.0988. Min Act: -0.1700

Data Index: 120173 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 5.7238. Min Range: -5.7238

Max Act: 5.1300. Min Act: -0.1700

Data Index: 535596 (C4 (Web Text))

Max Activating Token Index: 1023