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

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

Neuron 1090 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.9776. Min Act: -0.1700

Data Index: 886660 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.9776. Min Act: -0.1700

Data Index: 132619 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.9463. Min Act: -0.1700

Data Index: 349159 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.9776. Min Act: -0.1700

Data Index: 612047 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 5.0088. Min Range: -5.0088

Max Act: 5.0088. Min Act: -0.1700

Data Index: 1352937 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.9463. Min Act: -0.1700

Data Index: 1131214 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.9463. Min Act: -0.1700

Data Index: 56818 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.9151. Min Act: -0.1700

Data Index: 605424 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.9463. Min Act: -0.1700

Data Index: 737809 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.8526. Min Act: -0.1700

Data Index: 433924 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.8526. Min Act: -0.1700

Data Index: 1007385 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.8213. Min Act: -0.1700

Data Index: 1052198 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.8213. Min Act: -0.1700

Data Index: 157573 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.7901. Min Act: -0.1700

Data Index: 822704 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.8526. Min Act: -0.1700

Data Index: 521642 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.7901. Min Act: -0.1700

Data Index: 1125910 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.7588. Min Act: -0.1700

Data Index: 216309 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.7901. Min Act: -0.1700

Data Index: 713104 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.7901. Min Act: -0.1700

Data Index: 731466 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 5.0088. Min Range: -5.0088

Max Act: 4.7901. Min Act: -0.1700

Data Index: 126502 (C4 (Web Text))

Max Activating Token Index: 831