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

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

Neuron 1861 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: 5.6344. Min Range: -5.6344

Max Act: 5.6344. Min Act: -0.1700

Data Index: 610844 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.4781. Min Act: -0.1700

Data Index: 168984 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.5094. Min Act: -0.1700

Data Index: 1087580 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.5094. Min Act: -0.1700

Data Index: 1008233 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.4469. Min Act: -0.1700

Data Index: 962645 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.4469. Min Act: -0.1700

Data Index: 627826 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.3844. Min Act: -0.1700

Data Index: 755698 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.4469. Min Act: -0.1700

Data Index: 415761 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.3531. Min Act: -0.1700

Data Index: 632695 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.3844. Min Act: -0.1700

Data Index: 1176915 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.3844. Min Act: -0.1700

Data Index: 535181 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.3844. Min Act: -0.1700

Data Index: 88700 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.2906. Min Act: -0.1700

Data Index: 731016 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.2906. Min Act: -0.1700

Data Index: 599387 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.2594. Min Act: -0.1700

Data Index: 385222 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.2906. Min Act: -0.1700

Data Index: 1145803 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.3531. Min Act: -0.1700

Data Index: 458817 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.3531. Min Act: -0.1700

Data Index: 1355809 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.3219. Min Act: -0.1700

Data Index: 323372 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 5.6344. Min Range: -5.6344

Max Act: 5.2906. Min Act: -0.1700

Data Index: 63046 (C4 (Web Text))

Max Activating Token Index: 488