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

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

Neuron 763 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.6209. Min Act: -0.1700

Data Index: 452837 (C4 (Web Text))

Max Activating Token Index: 381

Text #1

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.5584. Min Act: -0.1699

Data Index: 375689 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.4647. Min Act: -0.1700

Data Index: 817437 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.3709. Min Act: -0.1700

Data Index: 1075360 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.4334. Min Act: -0.1700

Data Index: 734600 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.4334. Min Act: -0.1700

Data Index: 229283 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.3709. Min Act: -0.1700

Data Index: 612455 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.3397. Min Act: -0.1700

Data Index: 1145435 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.3709. Min Act: -0.1700

Data Index: 83917 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.3397. Min Act: -0.1700

Data Index: 764801 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.3397. Min Act: -0.1700

Data Index: 1071205 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.3397. Min Act: -0.1700

Data Index: 728339 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.3397. Min Act: -0.1699

Data Index: 881524 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.3397. Min Act: -0.1700

Data Index: 598548 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.3084. Min Act: -0.1700

Data Index: 774888 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.3397. Min Act: -0.1700

Data Index: 891277 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.3084. Min Act: -0.1700

Data Index: 372657 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.3397. Min Act: -0.1700

Data Index: 811898 (C4 (Web Text))

Max Activating Token Index: 886

Text #18

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.2459. Min Act: -0.1700

Data Index: 661190 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 5.6209. Min Range: -5.6209

Max Act: 5.2459. Min Act: -0.1700

Data Index: 867843 (C4 (Web Text))

Max Activating Token Index: 838