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

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

Neuron 34 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: 3.8213. Min Range: -3.8213

Max Act: 3.8213. Min Act: -0.1700

Data Index: 365641 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.7588. Min Act: -0.1700

Data Index: 290176 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.6649. Min Act: -0.1700

Data Index: 246891 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.6649. Min Act: -0.1700

Data Index: 982478 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.6805. Min Act: -0.1700

Data Index: 9680 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.6492. Min Act: -0.1700

Data Index: 449947 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.6649. Min Act: -0.1700

Data Index: 641542 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.6492. Min Act: -0.1700

Data Index: 1007114 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.6336. Min Act: -0.1700

Data Index: 1098580 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.6023. Min Act: -0.1700

Data Index: 1159602 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5866. Min Act: -0.1700

Data Index: 469506 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5866. Min Act: -0.1700

Data Index: 1175187 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5709. Min Act: -0.1700

Data Index: 35348 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.6336. Min Act: -0.1700

Data Index: 623930 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5709. Min Act: -0.1700

Data Index: 18092 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5709. Min Act: -0.1700

Data Index: 1000846 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5553. Min Act: -0.1700

Data Index: 852572 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5553. Min Act: -0.1700

Data Index: 915933 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5553. Min Act: -0.1700

Data Index: 916866 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5709. Min Act: -0.1700

Data Index: 208603 (C4 (Web Text))

Max Activating Token Index: 820