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

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

Neuron 1400 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: 3.3205. Min Range: -3.3205

Max Act: 3.3205. Min Act: -0.1700

Data Index: 627391 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.3205. Min Act: -0.1700

Data Index: 825301 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.3048. Min Act: -0.1700

Data Index: 565327 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.3048. Min Act: -0.1700

Data Index: 247782 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.2576. Min Act: -0.1700

Data Index: 274018 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.2891. Min Act: -0.1700

Data Index: 1067141 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.2891. Min Act: -0.1700

Data Index: 75947 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.2734. Min Act: -0.1700

Data Index: 1294541 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.1947. Min Act: -0.1700

Data Index: 509482 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.1947. Min Act: -0.1700

Data Index: 195762 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.1947. Min Act: -0.1700

Data Index: 1089572 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.1947. Min Act: -0.1700

Data Index: 886799 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.1790. Min Act: -0.1700

Data Index: 403509 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.1947. Min Act: -0.1700

Data Index: 1333953 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.1633. Min Act: -0.1700

Data Index: 136632 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.1790. Min Act: -0.1700

Data Index: 838372 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.1790. Min Act: -0.1700

Data Index: 196973 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.1475. Min Act: -0.1700

Data Index: 224589 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.1633. Min Act: -0.1700

Data Index: 116903 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 3.3205. Min Range: -3.3205

Max Act: 3.1633. Min Act: -0.1700

Data Index: 1216305 (C4 (Web Text))

Max Activating Token Index: 629