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

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

Neuron 255 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3971. Min Range: -5.3971

Max Act: 5.3971. Min Act: -0.1700

Data Index: 1385403 (Python Code)

Max Activating Token Index: 439

Text #1

Max Range: 5.3971. Min Range: -5.3971

Max Act: 5.3033. Min Act: -0.1700

Data Index: 1374808 (Python Code)

Max Activating Token Index: 974

Text #2

Max Range: 5.3971. Min Range: -5.3971

Max Act: 5.1783. Min Act: -0.1700

Data Index: 1380039 (Python Code)

Max Activating Token Index: 789

Text #3

Max Range: 5.3971. Min Range: -5.3971

Max Act: 5.1471. Min Act: -0.1700

Data Index: 1521914 (Python Code)

Max Activating Token Index: 744

Text #4

Max Range: 5.3971. Min Range: -5.3971

Max Act: 5.1158. Min Act: -0.1700

Data Index: 1423545 (Python Code)

Max Activating Token Index: 512

Text #5

Max Range: 5.3971. Min Range: -5.3971

Max Act: 5.1158. Min Act: -0.1700

Data Index: 1654959 (Python Code)

Max Activating Token Index: 356

Text #6

Max Range: 5.3971. Min Range: -5.3971

Max Act: 5.0846. Min Act: -0.1700

Data Index: 1525607 (Python Code)

Max Activating Token Index: 743

Text #7

Max Range: 5.3971. Min Range: -5.3971

Max Act: 5.0221. Min Act: -0.1700

Data Index: 1531635 (Python Code)

Max Activating Token Index: 744

Text #8

Max Range: 5.3971. Min Range: -5.3971

Max Act: 5.0533. Min Act: -0.1700

Data Index: 1621753 (Python Code)

Max Activating Token Index: 585

Text #9

Max Range: 5.3971. Min Range: -5.3971

Max Act: 4.9908. Min Act: -0.1700

Data Index: 1408614 (Python Code)

Max Activating Token Index: 668

Text #10

Max Range: 5.3971. Min Range: -5.3971

Max Act: 4.9908. Min Act: -0.1700

Data Index: 1375249 (Python Code)

Max Activating Token Index: 613

Text #11

Max Range: 5.3971. Min Range: -5.3971

Max Act: 4.9908. Min Act: -0.1700

Data Index: 1420312 (Python Code)

Max Activating Token Index: 692

Text #12

Max Range: 5.3971. Min Range: -5.3971

Max Act: 4.9596. Min Act: -0.1700

Data Index: 1574781 (Python Code)

Max Activating Token Index: 735

Text #13

Max Range: 5.3971. Min Range: -5.3971

Max Act: 4.9283. Min Act: -0.1700

Data Index: 1570462 (Python Code)

Max Activating Token Index: 540

Text #14

Max Range: 5.3971. Min Range: -5.3971

Max Act: 4.9596. Min Act: -0.1700

Data Index: 1409348 (Python Code)

Max Activating Token Index: 447

Text #15

Max Range: 5.3971. Min Range: -5.3971

Max Act: 4.9283. Min Act: -0.1700

Data Index: 1639567 (Python Code)

Max Activating Token Index: 497

Text #16

Max Range: 5.3971. Min Range: -5.3971

Max Act: 5.0533. Min Act: -0.1700

Data Index: 1519754 (Python Code)

Max Activating Token Index: 659

Text #17

Max Range: 5.3971. Min Range: -5.3971

Max Act: 4.9908. Min Act: -0.1700

Data Index: 1574049 (Python Code)

Max Activating Token Index: 343

Text #18

Max Range: 5.3971. Min Range: -5.3971

Max Act: 5.0533. Min Act: -0.1700

Data Index: 1504182 (Python Code)

Max Activating Token Index: 662

Text #19

Max Range: 5.3971. Min Range: -5.3971

Max Act: 4.9908. Min Act: -0.1700

Data Index: 1406386 (Python Code)

Max Activating Token Index: 745