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

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

Neuron 71 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.9967. Min Act: -0.1700

Data Index: 412357 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.7779. Min Act: -0.1700

Data Index: 1010442 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.6842. Min Act: -0.1700

Data Index: 1041756 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.6842. Min Act: -0.1700

Data Index: 403598 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.6217. Min Act: -0.1700

Data Index: 446155 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.5904. Min Act: -0.1700

Data Index: 810745 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.5904. Min Act: -0.1700

Data Index: 945952 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.5592. Min Act: -0.1700

Data Index: 672758 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.5279. Min Act: -0.1700

Data Index: 1040096 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.4967. Min Act: -0.1700

Data Index: 1163752 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.5279. Min Act: -0.1700

Data Index: 749109 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.4654. Min Act: -0.1700

Data Index: 583787 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.4654. Min Act: -0.1700

Data Index: 702857 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.4967. Min Act: -0.1700

Data Index: 100704 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.4654. Min Act: -0.1700

Data Index: 487155 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.4342. Min Act: -0.1700

Data Index: 89451 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.4654. Min Act: -0.1700

Data Index: 670732 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.4967. Min Act: -0.1700

Data Index: 1217181 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.4654. Min Act: -0.1700

Data Index: 543426 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 4.9967. Min Range: -4.9967

Max Act: 4.4342. Min Act: -0.1700

Data Index: 593483 (C4 (Web Text))

Max Activating Token Index: 1023