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

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

Neuron 1954 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: 4.9366. Min Range: -4.9366

Max Act: 4.9366. Min Act: -0.1700

Data Index: 1007825 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 4.9366. Min Range: -4.9366

Max Act: 4.8429. Min Act: -0.1700

Data Index: 344475 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 4.9366. Min Range: -4.9366

Max Act: 4.8116. Min Act: -0.1700

Data Index: 767850 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 4.9366. Min Range: -4.9366

Max Act: 4.8116. Min Act: -0.1700

Data Index: 1137156 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 4.9366. Min Range: -4.9366

Max Act: 4.7804. Min Act: -0.1700

Data Index: 239005 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 4.9366. Min Range: -4.9366

Max Act: 4.7804. Min Act: -0.1700

Data Index: 269581 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 4.9366. Min Range: -4.9366

Max Act: 4.7647. Min Act: -0.1700

Data Index: 754196 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 4.9366. Min Range: -4.9366

Max Act: 4.7804. Min Act: -0.1700

Data Index: 614518 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 4.9366. Min Range: -4.9366

Max Act: 4.7179. Min Act: -0.1700

Data Index: 444239 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 4.9366. Min Range: -4.9366

Max Act: 4.8116. Min Act: -0.1700

Data Index: 317888 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 4.9366. Min Range: -4.9366

Max Act: 4.7491. Min Act: -0.1700

Data Index: 1235618 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 4.9366. Min Range: -4.9366

Max Act: 4.7022. Min Act: -0.1700

Data Index: 1134766 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 4.9366. Min Range: -4.9366

Max Act: 4.7022. Min Act: -0.1700

Data Index: 1185063 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 4.9366. Min Range: -4.9366

Max Act: 4.7022. Min Act: -0.1700

Data Index: 1336620 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 4.9366. Min Range: -4.9366

Max Act: 4.6554. Min Act: -0.1700

Data Index: 860303 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 4.9366. Min Range: -4.9366

Max Act: 4.6866. Min Act: -0.1700

Data Index: 832454 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 4.9366. Min Range: -4.9366

Max Act: 4.7179. Min Act: -0.1700

Data Index: 551233 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 4.9366. Min Range: -4.9366

Max Act: 4.6710. Min Act: -0.1700

Data Index: 462855 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 4.9366. Min Range: -4.9366

Max Act: 4.6710. Min Act: -0.1700

Data Index: 470106 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 4.9366. Min Range: -4.9366

Max Act: 4.6241. Min Act: -0.1700

Data Index: 137947 (C4 (Web Text))

Max Activating Token Index: 561