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

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

Neuron 1853 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.4486. Min Act: -0.1700

Data Index: 6816 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.4329. Min Act: -0.1700

Data Index: 230677 (C4 (Web Text))

Max Activating Token Index: 997

Text #2

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3545. Min Act: -0.1698

Data Index: 595728 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3388. Min Act: -0.1700

Data Index: 151384 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3074. Min Act: -0.1698

Data Index: 958464 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3074. Min Act: -0.1700

Data Index: 294992 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3231. Min Act: -0.1700

Data Index: 184367 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3231. Min Act: -0.1700

Data Index: 607760 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3231. Min Act: -0.1700

Data Index: 69804 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3074. Min Act: -0.1700

Data Index: 1335449 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3074. Min Act: -0.1700

Data Index: 304581 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3074. Min Act: -0.1700

Data Index: 582713 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3074. Min Act: -0.1699

Data Index: 1335700 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3074. Min Act: -0.1700

Data Index: 778332 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.3074. Min Act: -0.1700

Data Index: 1220139 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.2917. Min Act: -0.1700

Data Index: 610669 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.2603. Min Act: -0.1699

Data Index: 603273 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.2760. Min Act: -0.1700

Data Index: 1318781 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.2760. Min Act: -0.1700

Data Index: 619305 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 3.4486. Min Range: -3.4486

Max Act: 3.2446. Min Act: -0.1700

Data Index: 835017 (C4 (Web Text))

Max Activating Token Index: 793