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

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

Neuron 1993 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.6509. Min Act: -0.1700

Data Index: 938822 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.5883. Min Act: -0.1700

Data Index: 63442 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.5727. Min Act: -0.1700

Data Index: 491468 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.5727. Min Act: -0.1700

Data Index: 740027 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.5727. Min Act: -0.1700

Data Index: 395600 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.5413. Min Act: -0.1700

Data Index: 402399 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.5413. Min Act: -0.1700

Data Index: 433414 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.5413. Min Act: -0.1700

Data Index: 596971 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.5570. Min Act: -0.1700

Data Index: 1121804 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.5257. Min Act: -0.1700

Data Index: 327721 (C4 (Web Text))

Max Activating Token Index: 765

Text #10

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.5413. Min Act: -0.1700

Data Index: 825532 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.5257. Min Act: -0.1700

Data Index: 263334 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.5570. Min Act: -0.1700

Data Index: 297099 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.5413. Min Act: -0.1700

Data Index: 1015591 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.5413. Min Act: -0.1700

Data Index: 164729 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.5413. Min Act: -0.1700

Data Index: 167839 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.5257. Min Act: -0.1700

Data Index: 1321919 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.5257. Min Act: -0.1700

Data Index: 602082 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.5413. Min Act: -0.1700

Data Index: 1276957 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 3.6509. Min Range: -3.6509

Max Act: 3.5413. Min Act: -0.1700

Data Index: 537137 (C4 (Web Text))

Max Activating Token Index: 630