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

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

Neuron 420 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: 3.7111. Min Range: -3.7111

Max Act: 3.7111. Min Act: -0.1700

Data Index: 986273 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.6798. Min Act: -0.1700

Data Index: 1024477 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5858. Min Act: -0.1700

Data Index: 450644 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5702. Min Act: -0.1700

Data Index: 860141 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5858. Min Act: -0.1700

Data Index: 835475 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5545. Min Act: -0.1700

Data Index: 876732 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5545. Min Act: -0.1700

Data Index: 1114784 (C4 (Web Text))

Max Activating Token Index: 891

Text #7

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5545. Min Act: -0.1700

Data Index: 1085931 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5389. Min Act: -0.1700

Data Index: 626489 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5545. Min Act: -0.1700

Data Index: 395680 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5232. Min Act: -0.1700

Data Index: 1248312 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5075. Min Act: -0.1700

Data Index: 1017738 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5075. Min Act: -0.1700

Data Index: 1256547 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5545. Min Act: -0.1700

Data Index: 975449 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.4919. Min Act: -0.1700

Data Index: 78998 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5232. Min Act: -0.1700

Data Index: 501794 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5075. Min Act: -0.1700

Data Index: 1032246 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5075. Min Act: -0.1700

Data Index: 345109 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5232. Min Act: -0.1700

Data Index: 1228543 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 3.7111. Min Range: -3.7111

Max Act: 3.5075. Min Act: -0.1700

Data Index: 1130867 (C4 (Web Text))

Max Activating Token Index: 975