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

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

Neuron 193 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.3249. Min Act: -0.1700

Data Index: 1598317 (Python Code)

Max Activating Token Index: 169

Text #1

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.2620. Min Act: -0.1700

Data Index: 380250 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.2778. Min Act: -0.1700

Data Index: 869051 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.2620. Min Act: -0.1700

Data Index: 1164897 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.1834. Min Act: -0.1700

Data Index: 342937 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.2778. Min Act: -0.1700

Data Index: 1480028 (Python Code)

Max Activating Token Index: 832

Text #6

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.2620. Min Act: -0.1700

Data Index: 1593350 (Python Code)

Max Activating Token Index: 41

Text #7

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.2306. Min Act: -0.1700

Data Index: 829232 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.2620. Min Act: -0.1700

Data Index: 1123759 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.2778. Min Act: -0.1700

Data Index: 1057485 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.1834. Min Act: -0.1700

Data Index: 1111095 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.2778. Min Act: -0.1700

Data Index: 884215 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.2149. Min Act: -0.1700

Data Index: 72377 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.1991. Min Act: -0.1700

Data Index: 62470 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.2149. Min Act: -0.1700

Data Index: 1136532 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.1991. Min Act: -0.1700

Data Index: 992568 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.2306. Min Act: -0.1700

Data Index: 722617 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.1991. Min Act: -0.1700

Data Index: 1015895 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.2306. Min Act: -0.1700

Data Index: 660127 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 3.3249. Min Range: -3.3249

Max Act: 3.1834. Min Act: -0.1700

Data Index: 646418 (C4 (Web Text))

Max Activating Token Index: 593