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

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

Neuron 1167 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: 3.5220. Min Range: -3.5220

Max Act: 3.5220. Min Act: -0.1700

Data Index: 979935 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4907. Min Act: -0.1700

Data Index: 1067537 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4750. Min Act: -0.1700

Data Index: 758446 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.4123. Min Act: -0.1700

Data Index: 605514 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.3966. Min Act: -0.1700

Data Index: 26284 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.3809. Min Act: -0.1700

Data Index: 914004 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.3652. Min Act: -0.1700

Data Index: 553431 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.3495. Min Act: -0.1700

Data Index: 664835 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.3338. Min Act: -0.1700

Data Index: 51100 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.3338. Min Act: -0.1700

Data Index: 118124 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.3181. Min Act: -0.1700

Data Index: 753829 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.3181. Min Act: -0.1700

Data Index: 1258455 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.2867. Min Act: -0.1700

Data Index: 1061450 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.3024. Min Act: -0.1700

Data Index: 353570 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.3024. Min Act: -0.1700

Data Index: 466868 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.2867. Min Act: -0.1700

Data Index: 1176101 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.2396. Min Act: -0.1700

Data Index: 601897 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.2239. Min Act: -0.1700

Data Index: 669705 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.2081. Min Act: -0.1700

Data Index: 983249 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 3.5220. Min Range: -3.5220

Max Act: 3.1767. Min Act: -0.1700

Data Index: 435712 (C4 (Web Text))

Max Activating Token Index: 353