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

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

Neuron 1587 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.2913. Min Act: -0.1700

Data Index: 360097 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.2598. Min Act: -0.1700

Data Index: 458475 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.2598. Min Act: -0.1700

Data Index: 927093 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.2598. Min Act: -0.1700

Data Index: 868446 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.2441. Min Act: -0.1700

Data Index: 559502 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.2127. Min Act: -0.1700

Data Index: 555735 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1969. Min Act: -0.1700

Data Index: 557420 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1655. Min Act: -0.1700

Data Index: 449995 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1655. Min Act: -0.1700

Data Index: 237140 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1655. Min Act: -0.1700

Data Index: 1309564 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1812. Min Act: -0.1700

Data Index: 952201 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1812. Min Act: -0.1700

Data Index: 374745 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1655. Min Act: -0.1700

Data Index: 273253 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1340. Min Act: -0.1700

Data Index: 515186 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1340. Min Act: -0.1700

Data Index: 1178918 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1497. Min Act: -0.1700

Data Index: 68300 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1340. Min Act: -0.1700

Data Index: 330094 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1340. Min Act: -0.1700

Data Index: 1304784 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1182. Min Act: -0.1700

Data Index: 614100 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 3.2913. Min Range: -3.2913

Max Act: 3.1340. Min Act: -0.1700

Data Index: 1263586 (C4 (Web Text))

Max Activating Token Index: 640