Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1170 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.2692. Min Range: -5.2692

Max Act: 5.2692. Min Act: -0.1700

Data Index: 1113560 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 5.2692. Min Range: -5.2692

Max Act: 5.0817. Min Act: -0.1700

Data Index: 31402 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 5.2692. Min Range: -5.2692

Max Act: 5.0504. Min Act: -0.1700

Data Index: 676864 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 5.2692. Min Range: -5.2692

Max Act: 4.9723. Min Act: -0.1700

Data Index: 933335 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 5.2692. Min Range: -5.2692

Max Act: 4.9879. Min Act: -0.1700

Data Index: 385442 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 5.2692. Min Range: -5.2692

Max Act: 5.0036. Min Act: -0.1700

Data Index: 1014713 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 5.2692. Min Range: -5.2692

Max Act: 4.9879. Min Act: -0.1700

Data Index: 1340201 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 5.2692. Min Range: -5.2692

Max Act: 4.9879. Min Act: -0.1700

Data Index: 569125 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 5.2692. Min Range: -5.2692

Max Act: 4.9879. Min Act: -0.1700

Data Index: 706707 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 5.2692. Min Range: -5.2692

Max Act: 4.9723. Min Act: -0.1700

Data Index: 947107 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 5.2692. Min Range: -5.2692

Max Act: 4.9879. Min Act: -0.1700

Data Index: 1106048 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 5.2692. Min Range: -5.2692

Max Act: 5.0036. Min Act: -0.1700

Data Index: 1310606 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 5.2692. Min Range: -5.2692

Max Act: 4.9411. Min Act: -0.1700

Data Index: 1324383 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 5.2692. Min Range: -5.2692

Max Act: 4.9723. Min Act: -0.1700

Data Index: 433628 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 5.2692. Min Range: -5.2692

Max Act: 4.9567. Min Act: -0.1700

Data Index: 354834 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 5.2692. Min Range: -5.2692

Max Act: 4.9567. Min Act: -0.1700

Data Index: 1208476 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 5.2692. Min Range: -5.2692

Max Act: 4.9098. Min Act: -0.1700

Data Index: 1198868 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 5.2692. Min Range: -5.2692

Max Act: 4.9254. Min Act: -0.1700

Data Index: 574922 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 5.2692. Min Range: -5.2692

Max Act: 4.9411. Min Act: -0.1700

Data Index: 988858 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 5.2692. Min Range: -5.2692

Max Act: 4.9411. Min Act: -0.1700

Data Index: 670237 (C4 (Web Text))

Max Activating Token Index: 215