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

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

Neuron 1387 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: 5.5030. Min Range: -5.5030

Max Act: 5.5030. Min Act: -0.1700

Data Index: 869631 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.5030. Min Range: -5.5030

Max Act: 5.3780. Min Act: -0.1700

Data Index: 72551 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 5.5030. Min Range: -5.5030

Max Act: 5.3155. Min Act: -0.1700

Data Index: 901347 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 5.5030. Min Range: -5.5030

Max Act: 5.2530. Min Act: -0.1700

Data Index: 220917 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 5.5030. Min Range: -5.5030

Max Act: 5.2530. Min Act: -0.1700

Data Index: 860431 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 5.5030. Min Range: -5.5030

Max Act: 5.2530. Min Act: -0.1700

Data Index: 623321 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 5.5030. Min Range: -5.5030

Max Act: 5.2842. Min Act: -0.1700

Data Index: 1241461 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 5.5030. Min Range: -5.5030

Max Act: 5.2530. Min Act: -0.1700

Data Index: 661735 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 5.5030. Min Range: -5.5030

Max Act: 5.2530. Min Act: -0.1700

Data Index: 613946 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 5.5030. Min Range: -5.5030

Max Act: 5.2217. Min Act: -0.1700

Data Index: 826120 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 5.5030. Min Range: -5.5030

Max Act: 5.1905. Min Act: -0.1700

Data Index: 1007469 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 5.5030. Min Range: -5.5030

Max Act: 5.0967. Min Act: -0.1700

Data Index: 1293812 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 5.5030. Min Range: -5.5030

Max Act: 5.1592. Min Act: -0.1700

Data Index: 683873 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 5.5030. Min Range: -5.5030

Max Act: 5.2217. Min Act: -0.1700

Data Index: 247795 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 5.5030. Min Range: -5.5030

Max Act: 5.1905. Min Act: -0.1700

Data Index: 570706 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 5.5030. Min Range: -5.5030

Max Act: 5.2530. Min Act: -0.1700

Data Index: 160947 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 5.5030. Min Range: -5.5030

Max Act: 5.1592. Min Act: -0.1700

Data Index: 1281476 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 5.5030. Min Range: -5.5030

Max Act: 5.2217. Min Act: -0.1700

Data Index: 623527 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 5.5030. Min Range: -5.5030

Max Act: 5.1592. Min Act: -0.1700

Data Index: 242661 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 5.5030. Min Range: -5.5030

Max Act: 5.1592. Min Act: -0.1700

Data Index: 652572 (C4 (Web Text))

Max Activating Token Index: 748