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

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

Neuron 812 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: 5.4045. Min Range: -5.4045

Max Act: 5.4045. Min Act: -0.1700

Data Index: 1449020 (Python Code)

Max Activating Token Index: 22

Text #1

Max Range: 5.4045. Min Range: -5.4045

Max Act: 5.2795. Min Act: -0.1700

Data Index: 1365363 (Python Code)

Max Activating Token Index: 687

Text #2

Max Range: 5.4045. Min Range: -5.4045

Max Act: 5.2795. Min Act: -0.1700

Data Index: 1541464 (Python Code)

Max Activating Token Index: 187

Text #3

Max Range: 5.4045. Min Range: -5.4045

Max Act: 5.2795. Min Act: -0.1700

Data Index: 1371590 (Python Code)

Max Activating Token Index: 637

Text #4

Max Range: 5.4045. Min Range: -5.4045

Max Act: 5.2795. Min Act: -0.1700

Data Index: 1488481 (Python Code)

Max Activating Token Index: 714

Text #5

Max Range: 5.4045. Min Range: -5.4045

Max Act: 5.2795. Min Act: -0.1700

Data Index: 1401185 (Python Code)

Max Activating Token Index: 589

Text #6

Max Range: 5.4045. Min Range: -5.4045

Max Act: 5.2795. Min Act: -0.1700

Data Index: 1466664 (Python Code)

Max Activating Token Index: 438

Text #7

Max Range: 5.4045. Min Range: -5.4045

Max Act: 5.1857. Min Act: -0.1700

Data Index: 1509190 (Python Code)

Max Activating Token Index: 794

Text #8

Max Range: 5.4045. Min Range: -5.4045

Max Act: 5.2170. Min Act: -0.1700

Data Index: 1522924 (Python Code)

Max Activating Token Index: 385

Text #9

Max Range: 5.4045. Min Range: -5.4045

Max Act: 5.1857. Min Act: -0.1700

Data Index: 1408215 (Python Code)

Max Activating Token Index: 863

Text #10

Max Range: 5.4045. Min Range: -5.4045

Max Act: 5.1857. Min Act: -0.1700

Data Index: 1484595 (Python Code)

Max Activating Token Index: 877

Text #11

Max Range: 5.4045. Min Range: -5.4045

Max Act: 5.2482. Min Act: -0.1700

Data Index: 1595385 (Python Code)

Max Activating Token Index: 574

Text #12

Max Range: 5.4045. Min Range: -5.4045

Max Act: 5.2482. Min Act: -0.1700

Data Index: 1437398 (Python Code)

Max Activating Token Index: 873

Text #13

Max Range: 5.4045. Min Range: -5.4045

Max Act: 5.2170. Min Act: -0.1700

Data Index: 1412133 (Python Code)

Max Activating Token Index: 851

Text #14

Max Range: 5.4045. Min Range: -5.4045

Max Act: 5.2170. Min Act: -0.1700

Data Index: 1368929 (Python Code)

Max Activating Token Index: 877

Text #15

Max Range: 5.4045. Min Range: -5.4045

Max Act: 5.2170. Min Act: -0.1700

Data Index: 1361318 (Python Code)

Max Activating Token Index: 544

Text #16

Max Range: 5.4045. Min Range: -5.4045

Max Act: 5.2170. Min Act: -0.1700

Data Index: 1431229 (Python Code)

Max Activating Token Index: 695

Text #17

Max Range: 5.4045. Min Range: -5.4045

Max Act: 5.2795. Min Act: -0.1700

Data Index: 1408174 (Python Code)

Max Activating Token Index: 633

Text #18

Max Range: 5.4045. Min Range: -5.4045

Max Act: 5.2170. Min Act: -0.1700

Data Index: 1379657 (Python Code)

Max Activating Token Index: 604

Text #19

Max Range: 5.4045. Min Range: -5.4045

Max Act: 5.1857. Min Act: -0.1700

Data Index: 1376281 (Python Code)

Max Activating Token Index: 700