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

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

Neuron 1555 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: 3.3455. Min Range: -3.3455

Max Act: 3.3455. Min Act: -0.1700

Data Index: 163219 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 3.3455. Min Range: -3.3455

Max Act: 3.3298. Min Act: -0.1700

Data Index: 624014 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 3.3455. Min Range: -3.3455

Max Act: 3.2827. Min Act: -0.1700

Data Index: 1046193 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 3.3455. Min Range: -3.3455

Max Act: 3.2670. Min Act: -0.1700

Data Index: 578473 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 3.3455. Min Range: -3.3455

Max Act: 3.2198. Min Act: -0.1700

Data Index: 1302462 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 3.3455. Min Range: -3.3455

Max Act: 3.1883. Min Act: -0.1700

Data Index: 475551 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 3.3455. Min Range: -3.3455

Max Act: 3.1726. Min Act: -0.1700

Data Index: 1347966 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 3.3455. Min Range: -3.3455

Max Act: 3.1883. Min Act: -0.1700

Data Index: 634211 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 3.3455. Min Range: -3.3455

Max Act: 3.2041. Min Act: -0.1700

Data Index: 613814 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 3.3455. Min Range: -3.3455

Max Act: 3.1568. Min Act: -0.1700

Data Index: 1096951 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 3.3455. Min Range: -3.3455

Max Act: 3.1568. Min Act: -0.1700

Data Index: 644627 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 3.3455. Min Range: -3.3455

Max Act: 3.1568. Min Act: -0.1700

Data Index: 1280673 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 3.3455. Min Range: -3.3455

Max Act: 3.1568. Min Act: -0.1700

Data Index: 507576 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 3.3455. Min Range: -3.3455

Max Act: 3.1411. Min Act: -0.1700

Data Index: 215629 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 3.3455. Min Range: -3.3455

Max Act: 3.1411. Min Act: -0.1700

Data Index: 1130233 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 3.3455. Min Range: -3.3455

Max Act: 3.1411. Min Act: -0.1700

Data Index: 251375 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 3.3455. Min Range: -3.3455

Max Act: 3.0938. Min Act: -0.1700

Data Index: 291816 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 3.3455. Min Range: -3.3455

Max Act: 3.1096. Min Act: -0.1700

Data Index: 1037159 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 3.3455. Min Range: -3.3455

Max Act: 3.0938. Min Act: -0.1700

Data Index: 1273134 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 3.3455. Min Range: -3.3455

Max Act: 3.1096. Min Act: -0.1700

Data Index: 1202946 (C4 (Web Text))

Max Activating Token Index: 5