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

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

Neuron 1461 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: 3.7573. Min Range: -3.7573

Max Act: 3.7573. Min Act: -0.1700

Data Index: 1337358 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 3.7573. Min Range: -3.7573

Max Act: 3.6008. Min Act: -0.1700

Data Index: 278339 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 3.7573. Min Range: -3.7573

Max Act: 3.5695. Min Act: -0.1700

Data Index: 1049264 (C4 (Web Text))

Max Activating Token Index: 514

Text #3

Max Range: 3.7573. Min Range: -3.7573

Max Act: 3.5068. Min Act: -0.1700

Data Index: 457286 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 3.7573. Min Range: -3.7573

Max Act: 3.5068. Min Act: -0.1700

Data Index: 1248802 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 3.7573. Min Range: -3.7573

Max Act: 3.5068. Min Act: -0.1700

Data Index: 517857 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 3.7573. Min Range: -3.7573

Max Act: 3.5068. Min Act: -0.1700

Data Index: 394572 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 3.7573. Min Range: -3.7573

Max Act: 3.4912. Min Act: -0.1700

Data Index: 737847 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 3.7573. Min Range: -3.7573

Max Act: 3.4755. Min Act: -0.1700

Data Index: 788529 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 3.7573. Min Range: -3.7573

Max Act: 3.4755. Min Act: -0.1700

Data Index: 1268835 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 3.7573. Min Range: -3.7573

Max Act: 3.4755. Min Act: -0.1700

Data Index: 138488 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 3.7573. Min Range: -3.7573

Max Act: 3.4598. Min Act: -0.1700

Data Index: 599360 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 3.7573. Min Range: -3.7573

Max Act: 3.4912. Min Act: -0.1700

Data Index: 360089 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 3.7573. Min Range: -3.7573

Max Act: 3.4598. Min Act: -0.1700

Data Index: 276747 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 3.7573. Min Range: -3.7573

Max Act: 3.4598. Min Act: -0.1700

Data Index: 810685 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 3.7573. Min Range: -3.7573

Max Act: 3.4441. Min Act: -0.1700

Data Index: 1322585 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 3.7573. Min Range: -3.7573

Max Act: 3.4441. Min Act: -0.1700

Data Index: 893861 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 3.7573. Min Range: -3.7573

Max Act: 3.4285. Min Act: -0.1700

Data Index: 37502 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 3.7573. Min Range: -3.7573

Max Act: 3.4441. Min Act: -0.1700

Data Index: 378217 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 3.7573. Min Range: -3.7573

Max Act: 3.4285. Min Act: -0.1700

Data Index: 443242 (C4 (Web Text))

Max Activating Token Index: 363