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

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

Neuron 1904 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: 5.8019. Min Range: -5.8019

Max Act: 5.8019. Min Act: -0.1700

Data Index: 1285215 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 5.8019. Min Range: -5.8019

Max Act: 5.8019. Min Act: -0.1700

Data Index: 938568 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 5.8019. Min Range: -5.8019

Max Act: 5.6769. Min Act: -0.1700

Data Index: 710320 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 5.8019. Min Range: -5.8019

Max Act: 5.6457. Min Act: -0.1700

Data Index: 478185 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 5.8019. Min Range: -5.8019

Max Act: 5.5832. Min Act: -0.1700

Data Index: 112199 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 5.8019. Min Range: -5.8019

Max Act: 5.6144. Min Act: -0.1700

Data Index: 1176794 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 5.8019. Min Range: -5.8019

Max Act: 5.6457. Min Act: -0.1700

Data Index: 676098 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 5.8019. Min Range: -5.8019

Max Act: 5.6144. Min Act: -0.1700

Data Index: 1107883 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 5.8019. Min Range: -5.8019

Max Act: 5.6144. Min Act: -0.1700

Data Index: 938098 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 5.8019. Min Range: -5.8019

Max Act: 5.5519. Min Act: -0.1700

Data Index: 254225 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 5.8019. Min Range: -5.8019

Max Act: 5.5832. Min Act: -0.1700

Data Index: 541299 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 5.8019. Min Range: -5.8019

Max Act: 5.5519. Min Act: -0.1700

Data Index: 513251 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 5.8019. Min Range: -5.8019

Max Act: 5.5519. Min Act: -0.1700

Data Index: 38505 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 5.8019. Min Range: -5.8019

Max Act: 5.4894. Min Act: -0.1700

Data Index: 36657 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 5.8019. Min Range: -5.8019

Max Act: 5.4582. Min Act: -0.1700

Data Index: 533366 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 5.8019. Min Range: -5.8019

Max Act: 5.4269. Min Act: -0.1700

Data Index: 930085 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 5.8019. Min Range: -5.8019

Max Act: 5.4269. Min Act: -0.1700

Data Index: 1174671 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 5.8019. Min Range: -5.8019

Max Act: 5.4269. Min Act: -0.1700

Data Index: 465587 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 5.8019. Min Range: -5.8019

Max Act: 5.4582. Min Act: -0.1700

Data Index: 1348924 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 5.8019. Min Range: -5.8019

Max Act: 5.4269. Min Act: -0.1700

Data Index: 561336 (C4 (Web Text))

Max Activating Token Index: 802