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

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

Neuron 1778 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: 3.2630. Min Range: -3.2630

Max Act: 3.2630. Min Act: -0.1700

Data Index: 1074869 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.2316. Min Act: -0.1700

Data Index: 1167102 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.2001. Min Act: -0.1700

Data Index: 301717 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.2001. Min Act: -0.1700

Data Index: 71921 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.2001. Min Act: -0.1700

Data Index: 953636 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.2001. Min Act: -0.1700

Data Index: 98249 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1844. Min Act: -0.1700

Data Index: 559319 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1687. Min Act: -0.1700

Data Index: 293178 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1687. Min Act: -0.1700

Data Index: 478649 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1687. Min Act: -0.1700

Data Index: 394161 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1687. Min Act: -0.1700

Data Index: 228255 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1529. Min Act: -0.1700

Data Index: 459401 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.0899. Min Act: -0.1700

Data Index: 845679 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1372. Min Act: -0.1700

Data Index: 877309 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1529. Min Act: -0.1700

Data Index: 40840 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1687. Min Act: -0.1700

Data Index: 1092512 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1687. Min Act: -0.1700

Data Index: 361005 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1687. Min Act: -0.1700

Data Index: 666609 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1687. Min Act: -0.1700

Data Index: 998356 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 3.2630. Min Range: -3.2630

Max Act: 3.1687. Min Act: -0.1700

Data Index: 612320 (C4 (Web Text))

Max Activating Token Index: 634