Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 365 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.3417. Min Range: -5.3417

Max Act: 5.3105. Min Act: -0.1700

Data Index: 1080896 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 5.3417. Min Range: -5.3417

Max Act: 5.3417. Min Act: -0.1700

Data Index: 341867 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 5.3417. Min Range: -5.3417

Max Act: 5.2792. Min Act: -0.1700

Data Index: 36084 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 5.3417. Min Range: -5.3417

Max Act: 5.2167. Min Act: -0.1700

Data Index: 1224429 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 5.3417. Min Range: -5.3417

Max Act: 5.1855. Min Act: -0.1700

Data Index: 805822 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 5.3417. Min Range: -5.3417

Max Act: 5.1230. Min Act: -0.1700

Data Index: 401149 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 5.3417. Min Range: -5.3417

Max Act: 5.1542. Min Act: -0.1700

Data Index: 835574 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 5.3417. Min Range: -5.3417

Max Act: 5.1230. Min Act: -0.1700

Data Index: 495494 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 5.3417. Min Range: -5.3417

Max Act: 5.1230. Min Act: -0.1700

Data Index: 452325 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 5.3417. Min Range: -5.3417

Max Act: 5.1542. Min Act: -0.1700

Data Index: 1296982 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 5.3417. Min Range: -5.3417

Max Act: 5.0605. Min Act: -0.1700

Data Index: 548774 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 5.3417. Min Range: -5.3417

Max Act: 5.0605. Min Act: -0.1700

Data Index: 160780 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 5.3417. Min Range: -5.3417

Max Act: 5.0917. Min Act: -0.1700

Data Index: 733974 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 5.3417. Min Range: -5.3417

Max Act: 5.0605. Min Act: -0.1700

Data Index: 69737 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 5.3417. Min Range: -5.3417

Max Act: 4.9980. Min Act: -0.1700

Data Index: 830114 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 5.3417. Min Range: -5.3417

Max Act: 5.0292. Min Act: -0.1700

Data Index: 1059195 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 5.3417. Min Range: -5.3417

Max Act: 4.9980. Min Act: -0.1700

Data Index: 812962 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 5.3417. Min Range: -5.3417

Max Act: 4.9667. Min Act: -0.1700

Data Index: 899212 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 5.3417. Min Range: -5.3417

Max Act: 4.9980. Min Act: -0.1700

Data Index: 625778 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 5.3417. Min Range: -5.3417

Max Act: 4.9980. Min Act: -0.1700

Data Index: 206364 (C4 (Web Text))

Max Activating Token Index: 756