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

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

Neuron 1232 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.4994. Min Act: -0.1700

Data Index: 586800 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.3426. Min Act: -0.1700

Data Index: 936901 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.3269. Min Act: -0.1700

Data Index: 1332140 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.2955. Min Act: -0.1700

Data Index: 557244 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.3112. Min Act: -0.1700

Data Index: 1310272 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.2798. Min Act: -0.1700

Data Index: 788770 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.2955. Min Act: -0.1700

Data Index: 154813 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.2641. Min Act: -0.1700

Data Index: 563716 (C4 (Web Text))

Max Activating Token Index: 736

Text #8

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.2955. Min Act: -0.1700

Data Index: 437740 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.2798. Min Act: -0.1700

Data Index: 825437 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.2641. Min Act: -0.1700

Data Index: 997363 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.2641. Min Act: -0.1700

Data Index: 1214023 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.2641. Min Act: -0.1700

Data Index: 514220 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.2641. Min Act: -0.1700

Data Index: 1086443 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.2798. Min Act: -0.1700

Data Index: 1302164 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.2641. Min Act: -0.1700

Data Index: 515244 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.2484. Min Act: -0.1700

Data Index: 148647 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.2484. Min Act: -0.1700

Data Index: 1072973 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.2798. Min Act: -0.1700

Data Index: 184122 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 3.4994. Min Range: -3.4994

Max Act: 3.2169. Min Act: -0.1700

Data Index: 965854 (C4 (Web Text))

Max Activating Token Index: 658