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

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

Neuron 101 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.7366. Min Act: -0.1700

Data Index: 639280 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.6741. Min Act: -0.1700

Data Index: 360992 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.6116. Min Act: -0.1700

Data Index: 1034967 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.6741. Min Act: -0.1700

Data Index: 1026719 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.6428. Min Act: -0.1700

Data Index: 117282 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.5803. Min Act: -0.1700

Data Index: 1061887 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.5178. Min Act: -0.1700

Data Index: 548621 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.5491. Min Act: -0.1700

Data Index: 433219 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.5178. Min Act: -0.1700

Data Index: 1266856 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.5178. Min Act: -0.1700

Data Index: 1078893 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.4866. Min Act: -0.1700

Data Index: 429709 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.5491. Min Act: -0.1700

Data Index: 313332 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.4553. Min Act: -0.1700

Data Index: 732406 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.4553. Min Act: -0.1700

Data Index: 1109019 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.4241. Min Act: -0.1700

Data Index: 113832 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.3928. Min Act: -0.1700

Data Index: 1062087 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.4241. Min Act: -0.1700

Data Index: 163134 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.4553. Min Act: -0.1700

Data Index: 211430 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.4241. Min Act: -0.1700

Data Index: 666610 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 5.7366. Min Range: -5.7366

Max Act: 5.3616. Min Act: -0.1700

Data Index: 974952 (C4 (Web Text))

Max Activating Token Index: 57