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

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

Neuron 1643 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: 5.2768. Min Range: -5.2768

Max Act: 5.2768. Min Act: -0.1700

Data Index: 1314967 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 5.2768. Min Range: -5.2768

Max Act: 5.2768. Min Act: -0.1700

Data Index: 964119 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 5.2768. Min Range: -5.2768

Max Act: 5.2768. Min Act: -0.1700

Data Index: 1213833 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 5.2768. Min Range: -5.2768

Max Act: 5.2143. Min Act: -0.1700

Data Index: 75343 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 5.2768. Min Range: -5.2768

Max Act: 5.2456. Min Act: -0.1700

Data Index: 47443 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 5.2768. Min Range: -5.2768

Max Act: 5.1831. Min Act: -0.1700

Data Index: 1231955 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 5.2768. Min Range: -5.2768

Max Act: 5.1206. Min Act: -0.1700

Data Index: 108540 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 5.2768. Min Range: -5.2768

Max Act: 5.1206. Min Act: -0.1700

Data Index: 1120790 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 5.2768. Min Range: -5.2768

Max Act: 5.0581. Min Act: -0.1700

Data Index: 162223 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 5.2768. Min Range: -5.2768

Max Act: 5.1206. Min Act: -0.1700

Data Index: 248853 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 5.2768. Min Range: -5.2768

Max Act: 5.1206. Min Act: -0.1700

Data Index: 402408 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 5.2768. Min Range: -5.2768

Max Act: 5.1206. Min Act: -0.1700

Data Index: 661664 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 5.2768. Min Range: -5.2768

Max Act: 5.0581. Min Act: -0.1699

Data Index: 443102 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 5.2768. Min Range: -5.2768

Max Act: 5.0893. Min Act: -0.1700

Data Index: 1205374 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 5.2768. Min Range: -5.2768

Max Act: 5.0581. Min Act: -0.1700

Data Index: 212422 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 5.2768. Min Range: -5.2768

Max Act: 5.0268. Min Act: -0.1700

Data Index: 1177747 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 5.2768. Min Range: -5.2768

Max Act: 5.0268. Min Act: -0.1700

Data Index: 855916 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 5.2768. Min Range: -5.2768

Max Act: 5.0268. Min Act: -0.1700

Data Index: 424823 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 5.2768. Min Range: -5.2768

Max Act: 5.0268. Min Act: -0.1700

Data Index: 683652 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 5.2768. Min Range: -5.2768

Max Act: 5.0268. Min Act: -0.1700

Data Index: 1022343 (C4 (Web Text))

Max Activating Token Index: 713