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

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

Neuron 1654 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.5009. Min Act: -0.1700

Data Index: 507226 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.5322. Min Act: -0.1700

Data Index: 595440 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.4696. Min Act: -0.1700

Data Index: 1147226 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.4696. Min Act: -0.1700

Data Index: 1077805 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.4696. Min Act: -0.1700

Data Index: 941274 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.4382. Min Act: -0.1700

Data Index: 2524 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.4382. Min Act: -0.1700

Data Index: 1300752 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.4696. Min Act: -0.1700

Data Index: 1167282 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.4696. Min Act: -0.1700

Data Index: 479687 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.4696. Min Act: -0.1700

Data Index: 1128186 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.4068. Min Act: -0.1700

Data Index: 669971 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.4382. Min Act: -0.1700

Data Index: 250634 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.4382. Min Act: -0.1700

Data Index: 1250803 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.4068. Min Act: -0.1700

Data Index: 750203 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.3755. Min Act: -0.1700

Data Index: 595698 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.3441. Min Act: -0.1700

Data Index: 1338955 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.3755. Min Act: -0.1700

Data Index: 389657 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.3755. Min Act: -0.1700

Data Index: 1123246 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.3755. Min Act: -0.1700

Data Index: 1090124 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 3.5322. Min Range: -3.5322

Max Act: 3.2970. Min Act: -0.1700

Data Index: 700000 (C4 (Web Text))

Max Activating Token Index: 820