Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 7 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.9531. Min Act: -0.1700

Data Index: 790273 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.8280. Min Act: -0.1700

Data Index: 1119473 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.8436. Min Act: -0.1700

Data Index: 779012 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.9062. Min Act: -0.1700

Data Index: 1251923 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.7654. Min Act: -0.1700

Data Index: 769695 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.7810. Min Act: -0.1700

Data Index: 655154 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.7654. Min Act: -0.1700

Data Index: 1246604 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.7654. Min Act: -0.1700

Data Index: 27030 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.7185. Min Act: -0.1700

Data Index: 1209036 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.7498. Min Act: -0.1700

Data Index: 391745 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.7498. Min Act: -0.1700

Data Index: 268219 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.7341. Min Act: -0.1700

Data Index: 996294 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.7028. Min Act: -0.1700

Data Index: 1085330 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.7498. Min Act: -0.1700

Data Index: 615492 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.7028. Min Act: -0.1700

Data Index: 783250 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.6715. Min Act: -0.1700

Data Index: 1228874 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.6715. Min Act: -0.1700

Data Index: 833808 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.7028. Min Act: -0.1700

Data Index: 647432 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.6872. Min Act: -0.1700

Data Index: 1160979 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 3.9531. Min Range: -3.9531

Max Act: 3.6559. Min Act: -0.1700

Data Index: 403724 (C4 (Web Text))

Max Activating Token Index: 185