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

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

Neuron 982 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.2858. Min Act: -0.1700

Data Index: 1006200 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.2546. Min Act: -0.1700

Data Index: 119489 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.3171. Min Act: -0.1700

Data Index: 502240 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.1921. Min Act: -0.1700

Data Index: 787215 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.1921. Min Act: -0.1700

Data Index: 252165 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.2233. Min Act: -0.1700

Data Index: 398421 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.1608. Min Act: -0.1700

Data Index: 550848 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.1608. Min Act: -0.1700

Data Index: 1055295 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.2233. Min Act: -0.1700

Data Index: 822468 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.1608. Min Act: -0.1700

Data Index: 264892 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.1296. Min Act: -0.1700

Data Index: 486059 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.1608. Min Act: -0.1700

Data Index: 16840 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.1608. Min Act: -0.1700

Data Index: 779194 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.0671. Min Act: -0.1700

Data Index: 558950 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.0671. Min Act: -0.1700

Data Index: 911293 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.0983. Min Act: -0.1700

Data Index: 293536 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.1296. Min Act: -0.1700

Data Index: 737035 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.1608. Min Act: -0.1700

Data Index: 1205826 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.0983. Min Act: -0.1699

Data Index: 1357341 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 5.3171. Min Range: -5.3171

Max Act: 5.1608. Min Act: -0.1699

Data Index: 769208 (C4 (Web Text))

Max Activating Token Index: 628