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

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

Neuron 120 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.4001. Min Act: -0.1700

Data Index: 1019769 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.2438. Min Act: -0.1700

Data Index: 771906 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.2438. Min Act: -0.1700

Data Index: 1058513 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.2438. Min Act: -0.1700

Data Index: 49008 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.1501. Min Act: -0.1700

Data Index: 920868 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.1813. Min Act: -0.1700

Data Index: 385842 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.1188. Min Act: -0.1700

Data Index: 490578 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.0876. Min Act: -0.1700

Data Index: 1272765 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.1188. Min Act: -0.1700

Data Index: 657340 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.0563. Min Act: -0.1700

Data Index: 789985 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.0876. Min Act: -0.1700

Data Index: 866672 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.0563. Min Act: -0.1700

Data Index: 80820 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.1188. Min Act: -0.1700

Data Index: 1353642 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.0563. Min Act: -0.1700

Data Index: 912044 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.0876. Min Act: -0.1700

Data Index: 672230 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.0251. Min Act: -0.1700

Data Index: 270968 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.0563. Min Act: -0.1700

Data Index: 945081 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.0251. Min Act: -0.1700

Data Index: 324051 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.0251. Min Act: -0.1700

Data Index: 962700 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 5.4001. Min Range: -5.4001

Max Act: 5.0563. Min Act: -0.1700

Data Index: 253083 (C4 (Web Text))

Max Activating Token Index: 770