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

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

Neuron 671 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: 3.1572. Min Range: -3.1572

Max Act: 3.1415. Min Act: -0.1700

Data Index: 217831 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 3.1572. Min Range: -3.1572

Max Act: 3.1572. Min Act: -0.1700

Data Index: 1204657 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 3.1572. Min Range: -3.1572

Max Act: 3.0784. Min Act: -0.1700

Data Index: 1338314 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 3.1572. Min Range: -3.1572

Max Act: 3.0626. Min Act: -0.1700

Data Index: 725321 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 3.1572. Min Range: -3.1572

Max Act: 3.0784. Min Act: -0.1700

Data Index: 1020341 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 3.1572. Min Range: -3.1572

Max Act: 3.0626. Min Act: -0.1700

Data Index: 981680 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 3.1572. Min Range: -3.1572

Max Act: 3.0469. Min Act: -0.1700

Data Index: 669305 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 3.1572. Min Range: -3.1572

Max Act: 3.0469. Min Act: -0.1700

Data Index: 498875 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 3.1572. Min Range: -3.1572

Max Act: 3.0469. Min Act: -0.1700

Data Index: 179930 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 3.1572. Min Range: -3.1572

Max Act: 3.0153. Min Act: -0.1700

Data Index: 1416141 (Python Code)

Max Activating Token Index: 945

Text #10

Max Range: 3.1572. Min Range: -3.1572

Max Act: 3.0311. Min Act: -0.1700

Data Index: 735685 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 3.1572. Min Range: -3.1572

Max Act: 3.0153. Min Act: -0.1700

Data Index: 955191 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 3.1572. Min Range: -3.1572

Max Act: 3.0153. Min Act: -0.1700

Data Index: 718780 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 3.1572. Min Range: -3.1572

Max Act: 2.9836. Min Act: -0.1700

Data Index: 1314970 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 3.1572. Min Range: -3.1572

Max Act: 2.9995. Min Act: -0.1700

Data Index: 1276858 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 3.1572. Min Range: -3.1572

Max Act: 3.0153. Min Act: -0.1700

Data Index: 165147 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 3.1572. Min Range: -3.1572

Max Act: 2.9995. Min Act: -0.1700

Data Index: 990114 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 3.1572. Min Range: -3.1572

Max Act: 3.0153. Min Act: -0.1700

Data Index: 793311 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 3.1572. Min Range: -3.1572

Max Act: 2.9836. Min Act: -0.1700

Data Index: 1167735 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 3.1572. Min Range: -3.1572

Max Act: 2.9995. Min Act: -0.1700

Data Index: 794269 (C4 (Web Text))

Max Activating Token Index: 41