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

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

Neuron 1157 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: 3.6753. Min Range: -3.6753

Max Act: 3.6753. Min Act: -0.1700

Data Index: 1143979 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 3.6753. Min Range: -3.6753

Max Act: 3.6753. Min Act: -0.1700

Data Index: 60120 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 3.6753. Min Range: -3.6753

Max Act: 3.6127. Min Act: -0.1700

Data Index: 105941 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 3.6753. Min Range: -3.6753

Max Act: 3.6127. Min Act: -0.1700

Data Index: 499702 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 3.6753. Min Range: -3.6753

Max Act: 3.6127. Min Act: -0.1700

Data Index: 1274879 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 3.6753. Min Range: -3.6753

Max Act: 3.6127. Min Act: -0.1700

Data Index: 197107 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 3.6753. Min Range: -3.6753

Max Act: 3.6440. Min Act: -0.1700

Data Index: 1091168 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 3.6753. Min Range: -3.6753

Max Act: 3.6127. Min Act: -0.1700

Data Index: 179152 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 3.6753. Min Range: -3.6753

Max Act: 3.6127. Min Act: -0.1700

Data Index: 777089 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 3.6753. Min Range: -3.6753

Max Act: 3.5500. Min Act: -0.1700

Data Index: 362287 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 3.6753. Min Range: -3.6753

Max Act: 3.5813. Min Act: -0.1700

Data Index: 19197 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 3.6753. Min Range: -3.6753

Max Act: 3.5813. Min Act: -0.1700

Data Index: 713734 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 3.6753. Min Range: -3.6753

Max Act: 3.5813. Min Act: -0.1700

Data Index: 699132 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 3.6753. Min Range: -3.6753

Max Act: 3.5813. Min Act: -0.1700

Data Index: 805045 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 3.6753. Min Range: -3.6753

Max Act: 3.5500. Min Act: -0.1700

Data Index: 179699 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 3.6753. Min Range: -3.6753

Max Act: 3.5187. Min Act: -0.1700

Data Index: 1245100 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 3.6753. Min Range: -3.6753

Max Act: 3.5500. Min Act: -0.1700

Data Index: 142001 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 3.6753. Min Range: -3.6753

Max Act: 3.5500. Min Act: -0.1700

Data Index: 751236 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 3.6753. Min Range: -3.6753

Max Act: 3.5187. Min Act: -0.1700

Data Index: 595823 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 3.6753. Min Range: -3.6753

Max Act: 3.5187. Min Act: -0.1700

Data Index: 10857 (C4 (Web Text))

Max Activating Token Index: 724