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

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

Neuron 905 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: 5.3623. Min Range: -5.3623

Max Act: 5.2998. Min Act: -0.1700

Data Index: 978053 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.3623. Min Act: -0.1700

Data Index: 1115668 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.2686. Min Act: -0.1700

Data Index: 253 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.2373. Min Act: -0.1700

Data Index: 190384 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.2373. Min Act: -0.1700

Data Index: 131062 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.2686. Min Act: -0.1700

Data Index: 1245524 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.2998. Min Act: -0.1700

Data Index: 63446 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.2998. Min Act: -0.1700

Data Index: 237202 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.2686. Min Act: -0.1700

Data Index: 1135267 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.1748. Min Act: -0.1700

Data Index: 460594 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.2061. Min Act: -0.1700

Data Index: 975238 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.2061. Min Act: -0.1700

Data Index: 397033 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.0498. Min Act: -0.1700

Data Index: 941397 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.1436. Min Act: -0.1700

Data Index: 846861 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.1436. Min Act: -0.1700

Data Index: 602995 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.1436. Min Act: -0.1699

Data Index: 514002 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.1436. Min Act: -0.1700

Data Index: 394335 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.2061. Min Act: -0.1700

Data Index: 377833 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.1123. Min Act: -0.1700

Data Index: 1110826 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 5.3623. Min Range: -5.3623

Max Act: 5.1123. Min Act: -0.1700

Data Index: 34547 (C4 (Web Text))

Max Activating Token Index: 165