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

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

Neuron 459 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: 3.7879. Min Range: -3.7879

Max Act: 3.7879. Min Act: -0.1700

Data Index: 17133 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 3.7879. Min Range: -3.7879

Max Act: 3.7566. Min Act: -0.1700

Data Index: 1326147 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 3.7879. Min Range: -3.7879

Max Act: 3.7566. Min Act: -0.1700

Data Index: 764298 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 3.7879. Min Range: -3.7879

Max Act: 3.6314. Min Act: -0.1700

Data Index: 726598 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 3.7879. Min Range: -3.7879

Max Act: 3.6001. Min Act: -0.1700

Data Index: 1325738 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 3.7879. Min Range: -3.7879

Max Act: 3.5218. Min Act: -0.1700

Data Index: 1644582 (Python Code)

Max Activating Token Index: 673

Text #6

Max Range: 3.7879. Min Range: -3.7879

Max Act: 3.1922. Min Act: -0.1700

Data Index: 622648 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 3.7879. Min Range: -3.7879

Max Act: 3.1607. Min Act: -0.1700

Data Index: 136071 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 3.7879. Min Range: -3.7879

Max Act: 3.1292. Min Act: -0.1700

Data Index: 103316 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 3.7879. Min Range: -3.7879

Max Act: 3.0977. Min Act: -0.1700

Data Index: 1272713 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 3.7879. Min Range: -3.7879

Max Act: 3.1134. Min Act: -0.1700

Data Index: 88459 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 3.7879. Min Range: -3.7879

Max Act: 3.0819. Min Act: -0.1699

Data Index: 86054 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 3.7879. Min Range: -3.7879

Max Act: 3.0977. Min Act: -0.1700

Data Index: 493518 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 3.7879. Min Range: -3.7879

Max Act: 3.0819. Min Act: -0.1700

Data Index: 575654 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 3.7879. Min Range: -3.7879

Max Act: 3.0503. Min Act: -0.1700

Data Index: 1245663 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 3.7879. Min Range: -3.7879

Max Act: 3.0819. Min Act: -0.1700

Data Index: 1290094 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 3.7879. Min Range: -3.7879

Max Act: 3.0819. Min Act: -0.1700

Data Index: 582005 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 3.7879. Min Range: -3.7879

Max Act: 3.0503. Min Act: -0.1700

Data Index: 1301054 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 3.7879. Min Range: -3.7879

Max Act: 3.0819. Min Act: -0.1700

Data Index: 936922 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 3.7879. Min Range: -3.7879

Max Act: 3.0661. Min Act: -0.1700

Data Index: 620134 (C4 (Web Text))

Max Activating Token Index: 410