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

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

Neuron 1544 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: 3.2847. Min Range: -3.2847

Max Act: 3.2847. Min Act: -0.1700

Data Index: 964778 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 3.2847. Min Range: -3.2847

Max Act: 3.2218. Min Act: -0.1700

Data Index: 1188428 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 3.2847. Min Range: -3.2847

Max Act: 3.2375. Min Act: -0.1700

Data Index: 1194005 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 3.2847. Min Range: -3.2847

Max Act: 3.2375. Min Act: -0.1700

Data Index: 976608 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 3.2847. Min Range: -3.2847

Max Act: 3.1746. Min Act: -0.1700

Data Index: 839999 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 3.2847. Min Range: -3.2847

Max Act: 3.1903. Min Act: -0.1700

Data Index: 814524 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 3.2847. Min Range: -3.2847

Max Act: 3.2061. Min Act: -0.1700

Data Index: 1094962 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 3.2847. Min Range: -3.2847

Max Act: 3.1903. Min Act: -0.1700

Data Index: 923320 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 3.2847. Min Range: -3.2847

Max Act: 3.1746. Min Act: -0.1700

Data Index: 593313 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 3.2847. Min Range: -3.2847

Max Act: 3.1588. Min Act: -0.1700

Data Index: 433876 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 3.2847. Min Range: -3.2847

Max Act: 3.1746. Min Act: -0.1700

Data Index: 582927 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 3.2847. Min Range: -3.2847

Max Act: 3.1431. Min Act: -0.1700

Data Index: 1086379 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 3.2847. Min Range: -3.2847

Max Act: 3.1431. Min Act: -0.1700

Data Index: 481764 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 3.2847. Min Range: -3.2847

Max Act: 3.1588. Min Act: -0.1700

Data Index: 1274228 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 3.2847. Min Range: -3.2847

Max Act: 3.1588. Min Act: -0.1700

Data Index: 1214954 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 3.2847. Min Range: -3.2847

Max Act: 3.1588. Min Act: -0.1700

Data Index: 444897 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 3.2847. Min Range: -3.2847

Max Act: 3.1431. Min Act: -0.1700

Data Index: 423461 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 3.2847. Min Range: -3.2847

Max Act: 3.1273. Min Act: -0.1700

Data Index: 1063198 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 3.2847. Min Range: -3.2847

Max Act: 3.1116. Min Act: -0.1700

Data Index: 457747 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 3.2847. Min Range: -3.2847

Max Act: 3.1431. Min Act: -0.1700

Data Index: 1335121 (C4 (Web Text))

Max Activating Token Index: 39