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

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

Neuron 1896 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1977. Min Range: -4.1977

Max Act: 4.1977. Min Act: -0.1700

Data Index: 428681 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 4.1977. Min Range: -4.1977

Max Act: 3.9632. Min Act: -0.1700

Data Index: 836017 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 4.1977. Min Range: -4.1977

Max Act: 3.9476. Min Act: -0.1700

Data Index: 1052861 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 4.1977. Min Range: -4.1977

Max Act: 3.9476. Min Act: -0.1700

Data Index: 797934 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 4.1977. Min Range: -4.1977

Max Act: 3.8538. Min Act: -0.1700

Data Index: 1221717 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 4.1977. Min Range: -4.1977

Max Act: 3.8381. Min Act: -0.1700

Data Index: 1321640 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 4.1977. Min Range: -4.1977

Max Act: 3.8694. Min Act: -0.1700

Data Index: 305409 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 4.1977. Min Range: -4.1977

Max Act: 3.8069. Min Act: -0.1700

Data Index: 846200 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 4.1977. Min Range: -4.1977

Max Act: 3.8381. Min Act: -0.1700

Data Index: 771292 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 4.1977. Min Range: -4.1977

Max Act: 3.7756. Min Act: -0.1700

Data Index: 1133853 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 4.1977. Min Range: -4.1977

Max Act: 3.7912. Min Act: -0.1700

Data Index: 911208 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 4.1977. Min Range: -4.1977

Max Act: 3.8225. Min Act: -0.1700

Data Index: 774239 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 4.1977. Min Range: -4.1977

Max Act: 3.7599. Min Act: -0.1700

Data Index: 885254 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 4.1977. Min Range: -4.1977

Max Act: 3.7599. Min Act: -0.1700

Data Index: 936681 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 4.1977. Min Range: -4.1977

Max Act: 3.7443. Min Act: -0.1700

Data Index: 915298 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 4.1977. Min Range: -4.1977

Max Act: 3.7286. Min Act: -0.1700

Data Index: 461796 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 4.1977. Min Range: -4.1977

Max Act: 3.7443. Min Act: -0.1700

Data Index: 310426 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 4.1977. Min Range: -4.1977

Max Act: 3.7130. Min Act: -0.1700

Data Index: 513454 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 4.1977. Min Range: -4.1977

Max Act: 3.7286. Min Act: -0.1700

Data Index: 124216 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 4.1977. Min Range: -4.1977

Max Act: 3.7286. Min Act: -0.1700

Data Index: 109177 (C4 (Web Text))

Max Activating Token Index: 273