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

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

Neuron 1104 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.2692. Min Act: -0.1700

Data Index: 115142 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.2849. Min Act: -0.1700

Data Index: 1339406 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.2535. Min Act: -0.1700

Data Index: 871380 (C4 (Web Text))

Max Activating Token Index: 225

Text #3

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.2535. Min Act: -0.1700

Data Index: 905332 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.2220. Min Act: -0.1700

Data Index: 628927 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.2063. Min Act: -0.1700

Data Index: 1347767 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.1906. Min Act: -0.1700

Data Index: 992979 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.2220. Min Act: -0.1700

Data Index: 325894 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.2063. Min Act: -0.1700

Data Index: 1136782 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.2063. Min Act: -0.1700

Data Index: 866627 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.1748. Min Act: -0.1700

Data Index: 560989 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.1906. Min Act: -0.1700

Data Index: 356352 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.1748. Min Act: -0.1700

Data Index: 384244 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.1748. Min Act: -0.1700

Data Index: 395188 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.1433. Min Act: -0.1700

Data Index: 1175305 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.1748. Min Act: -0.1700

Data Index: 460987 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.1748. Min Act: -0.1700

Data Index: 1108951 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.1433. Min Act: -0.1700

Data Index: 681795 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.1591. Min Act: -0.1700

Data Index: 949547 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 3.2849. Min Range: -3.2849

Max Act: 3.1591. Min Act: -0.1700

Data Index: 195944 (C4 (Web Text))

Max Activating Token Index: 843