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

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

Neuron 321 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: 5.3129. Min Range: -5.3129

Max Act: 5.3129. Min Act: -0.1700

Data Index: 443457 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 5.3129. Min Range: -5.3129

Max Act: 5.0629. Min Act: -0.1700

Data Index: 1236752 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 5.3129. Min Range: -5.3129

Max Act: 5.0942. Min Act: -0.1700

Data Index: 228752 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 5.3129. Min Range: -5.3129

Max Act: 5.0629. Min Act: -0.1700

Data Index: 295701 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 5.3129. Min Range: -5.3129

Max Act: 5.0317. Min Act: -0.1700

Data Index: 567266 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 5.3129. Min Range: -5.3129

Max Act: 5.0004. Min Act: -0.1700

Data Index: 905059 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 5.3129. Min Range: -5.3129

Max Act: 4.9379. Min Act: -0.1700

Data Index: 1576459 (Python Code)

Max Activating Token Index: 868

Text #7

Max Range: 5.3129. Min Range: -5.3129

Max Act: 4.9692. Min Act: -0.1700

Data Index: 999578 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 5.3129. Min Range: -5.3129

Max Act: 4.8754. Min Act: -0.1700

Data Index: 1642926 (Python Code)

Max Activating Token Index: 748

Text #9

Max Range: 5.3129. Min Range: -5.3129

Max Act: 4.9067. Min Act: -0.1700

Data Index: 1273274 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 5.3129. Min Range: -5.3129

Max Act: 4.9067. Min Act: -0.1700

Data Index: 898750 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 5.3129. Min Range: -5.3129

Max Act: 4.9067. Min Act: -0.1700

Data Index: 1290524 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 5.3129. Min Range: -5.3129

Max Act: 4.9067. Min Act: -0.1700

Data Index: 1575521 (Python Code)

Max Activating Token Index: 796

Text #13

Max Range: 5.3129. Min Range: -5.3129

Max Act: 4.9067. Min Act: -0.1700

Data Index: 1621091 (Python Code)

Max Activating Token Index: 837

Text #14

Max Range: 5.3129. Min Range: -5.3129

Max Act: 4.8129. Min Act: -0.1700

Data Index: 1411274 (Python Code)

Max Activating Token Index: 556

Text #15

Max Range: 5.3129. Min Range: -5.3129

Max Act: 4.8754. Min Act: -0.1700

Data Index: 1325211 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 5.3129. Min Range: -5.3129

Max Act: 4.8754. Min Act: -0.1700

Data Index: 1092083 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 5.3129. Min Range: -5.3129

Max Act: 4.8129. Min Act: -0.1700

Data Index: 120534 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 5.3129. Min Range: -5.3129

Max Act: 4.7817. Min Act: -0.1700

Data Index: 1438727 (Python Code)

Max Activating Token Index: 854

Text #19

Max Range: 5.3129. Min Range: -5.3129

Max Act: 4.8754. Min Act: -0.1700

Data Index: 1451247 (Python Code)

Max Activating Token Index: 402