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

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

Neuron 1678 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: 3.4671. Min Range: -3.4671

Max Act: 3.4671. Min Act: -0.1700

Data Index: 1631451 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.4671. Min Range: -3.4671

Max Act: 3.4044. Min Act: -0.1699

Data Index: 1413613 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.4671. Min Range: -3.4671

Max Act: 3.3102. Min Act: -0.1625

Data Index: 1551655 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.4671. Min Range: -3.4671

Max Act: 3.2788. Min Act: -0.1700

Data Index: 1588740 (Python Code)

Max Activating Token Index: 500

Text #4

Max Range: 3.4671. Min Range: -3.4671

Max Act: 3.2788. Min Act: -0.1700

Data Index: 1598598 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.4671. Min Range: -3.4671

Max Act: 3.2788. Min Act: -0.1700

Data Index: 1629939 (Python Code)

Max Activating Token Index: 384

Text #6

Max Range: 3.4671. Min Range: -3.4671

Max Act: 3.2788. Min Act: -0.1700

Data Index: 1520422 (Python Code)

Max Activating Token Index: 679

Text #7

Max Range: 3.4671. Min Range: -3.4671

Max Act: 3.2159. Min Act: -0.1700

Data Index: 1599451 (Python Code)

Max Activating Token Index: 911

Text #8

Max Range: 3.4671. Min Range: -3.4671

Max Act: 3.2474. Min Act: -0.1700

Data Index: 1375510 (Python Code)

Max Activating Token Index: 245

Text #9

Max Range: 3.4671. Min Range: -3.4671

Max Act: 3.2159. Min Act: -0.1700

Data Index: 1624182 (Python Code)

Max Activating Token Index: 597

Text #10

Max Range: 3.4671. Min Range: -3.4671

Max Act: 3.2159. Min Act: -0.1700

Data Index: 1556194 (Python Code)

Max Activating Token Index: 470

Text #11

Max Range: 3.4671. Min Range: -3.4671

Max Act: 3.2159. Min Act: -0.1700

Data Index: 1527855 (Python Code)

Max Activating Token Index: 178

Text #12

Max Range: 3.4671. Min Range: -3.4671

Max Act: 3.1687. Min Act: -0.1700

Data Index: 1505450 (Python Code)

Max Activating Token Index: 528

Text #13

Max Range: 3.4671. Min Range: -3.4671

Max Act: 3.2159. Min Act: -0.1700

Data Index: 1650466 (Python Code)

Max Activating Token Index: 942

Text #14

Max Range: 3.4671. Min Range: -3.4671

Max Act: 3.1687. Min Act: -0.1700

Data Index: 1579545 (Python Code)

Max Activating Token Index: 473

Text #15

Max Range: 3.4671. Min Range: -3.4671

Max Act: 3.2159. Min Act: -0.1700

Data Index: 1526603 (Python Code)

Max Activating Token Index: 863

Text #16

Max Range: 3.4671. Min Range: -3.4671

Max Act: 3.1845. Min Act: -0.1700

Data Index: 1520343 (Python Code)

Max Activating Token Index: 682

Text #17

Max Range: 3.4671. Min Range: -3.4671

Max Act: 3.2002. Min Act: -0.1694

Data Index: 1586009 (Python Code)

Max Activating Token Index: 975

Text #18

Max Range: 3.4671. Min Range: -3.4671

Max Act: 3.2159. Min Act: -0.1700

Data Index: 1492471 (Python Code)

Max Activating Token Index: 864

Text #19

Max Range: 3.4671. Min Range: -3.4671

Max Act: 3.2002. Min Act: -0.1700

Data Index: 1619460 (Python Code)

Max Activating Token Index: 887