Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 426 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1351. Min Range: -3.1351

Max Act: 3.1351. Min Act: -0.1700

Data Index: 966351 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 3.1351. Min Range: -3.1351

Max Act: 3.0878. Min Act: -0.1700

Data Index: 928184 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 3.1351. Min Range: -3.1351

Max Act: 3.1036. Min Act: -0.1700

Data Index: 869053 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 3.1351. Min Range: -3.1351

Max Act: 3.0721. Min Act: -0.1700

Data Index: 531529 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 3.1351. Min Range: -3.1351

Max Act: 3.0878. Min Act: -0.1700

Data Index: 874176 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 3.1351. Min Range: -3.1351

Max Act: 3.0721. Min Act: -0.1700

Data Index: 1140225 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 3.1351. Min Range: -3.1351

Max Act: 3.0405. Min Act: -0.1700

Data Index: 377213 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 3.1351. Min Range: -3.1351

Max Act: 3.0247. Min Act: -0.1700

Data Index: 351727 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 3.1351. Min Range: -3.1351

Max Act: 3.0405. Min Act: -0.1700

Data Index: 245814 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 3.1351. Min Range: -3.1351

Max Act: 3.0405. Min Act: -0.1700

Data Index: 1146381 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 3.1351. Min Range: -3.1351

Max Act: 3.0247. Min Act: -0.1700

Data Index: 1171422 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 3.1351. Min Range: -3.1351

Max Act: 2.9931. Min Act: -0.1700

Data Index: 964438 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 3.1351. Min Range: -3.1351

Max Act: 3.0247. Min Act: -0.1700

Data Index: 333014 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 3.1351. Min Range: -3.1351

Max Act: 3.0089. Min Act: -0.1700

Data Index: 793869 (C4 (Web Text))

Max Activating Token Index: 216

Text #14

Max Range: 3.1351. Min Range: -3.1351

Max Act: 2.9931. Min Act: -0.1700

Data Index: 743608 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 3.1351. Min Range: -3.1351

Max Act: 3.0247. Min Act: -0.1700

Data Index: 1327650 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 3.1351. Min Range: -3.1351

Max Act: 2.9931. Min Act: -0.1700

Data Index: 1341464 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 3.1351. Min Range: -3.1351

Max Act: 2.9614. Min Act: -0.1700

Data Index: 728679 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 3.1351. Min Range: -3.1351

Max Act: 2.9614. Min Act: -0.1700

Data Index: 792832 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 3.1351. Min Range: -3.1351

Max Act: 2.9456. Min Act: -0.1700

Data Index: 731287 (C4 (Web Text))

Max Activating Token Index: 953