Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 117 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.4404. Min Act: -0.1700

Data Index: 481499 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.3620. Min Act: -0.1700

Data Index: 238453 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.3776. Min Act: -0.1700

Data Index: 1372316 (Python Code)

Max Activating Token Index: 101

Text #3

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.3620. Min Act: -0.1700

Data Index: 1433555 (Python Code)

Max Activating Token Index: 56

Text #4

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.3776. Min Act: -0.1700

Data Index: 1627948 (Python Code)

Max Activating Token Index: 47

Text #5

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.3620. Min Act: -0.1700

Data Index: 1278787 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.3463. Min Act: -0.1700

Data Index: 1433374 (Python Code)

Max Activating Token Index: 49

Text #7

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.3620. Min Act: -0.1700

Data Index: 498149 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.3463. Min Act: -0.1700

Data Index: 1381035 (Python Code)

Max Activating Token Index: 76

Text #9

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.3463. Min Act: -0.1700

Data Index: 1374990 (Python Code)

Max Activating Token Index: 472

Text #10

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.3149. Min Act: -0.1700

Data Index: 864577 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.2992. Min Act: -0.1700

Data Index: 1187708 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.3306. Min Act: -0.1700

Data Index: 1622149 (Python Code)

Max Activating Token Index: 39

Text #13

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.3306. Min Act: -0.1700

Data Index: 1379614 (Python Code)

Max Activating Token Index: 39

Text #14

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.3306. Min Act: -0.1700

Data Index: 1013090 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.3149. Min Act: -0.1700

Data Index: 637227 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.3149. Min Act: -0.1700

Data Index: 22518 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.3463. Min Act: -0.1700

Data Index: 268126 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.3306. Min Act: -0.1700

Data Index: 1065371 (C4 (Web Text))

Max Activating Token Index: 471

Text #19

Max Range: 3.4404. Min Range: -3.4404

Max Act: 3.2992. Min Act: -0.1700

Data Index: 1587813 (Python Code)

Max Activating Token Index: 73