Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1963 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.9913. Min Act: -0.1700

Data Index: 859254 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.9492. Min Act: -0.1673

Data Index: 197979 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.8384. Min Act: -0.1700

Data Index: 603375 (C4 (Web Text))

Max Activating Token Index: 290

Text #3

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.7845. Min Act: -0.1700

Data Index: 1029480 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.7462. Min Act: -0.1700

Data Index: 888431 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.7477. Min Act: -0.1700

Data Index: 19700 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.6842. Min Act: -0.1700

Data Index: 210129 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.6812. Min Act: -0.1700

Data Index: 411226 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.6829. Min Act: -0.1700

Data Index: 160608 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.6716. Min Act: -0.1700

Data Index: 61901 (C4 (Web Text))

Max Activating Token Index: 391

Text #10

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.6434. Min Act: -0.1700

Data Index: 1207999 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.6622. Min Act: -0.1700

Data Index: 60183 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.6616. Min Act: -0.1700

Data Index: 241721 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.6107. Min Act: -0.1700

Data Index: 1329891 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.5960. Min Act: -0.1700

Data Index: 681352 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.5832. Min Act: -0.1700

Data Index: 180426 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.5408. Min Act: -0.1700

Data Index: 706372 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.5526. Min Act: -0.1700

Data Index: 1258476 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.5094. Min Act: -0.1700

Data Index: 1548145 (Python Code)

Max Activating Token Index: 13

Text #19

Max Range: 5.9913. Min Range: -5.9913

Max Act: 5.5223. Min Act: -0.1700

Data Index: 443571 (C4 (Web Text))

Max Activating Token Index: 762