Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2454 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0484. Min Range: -1.0484

Max Act: 1.0484. Min Act: -0.0001

Data Index: 902156 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.9907. Min Act: -0.0001

Data Index: 888127 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.9717. Min Act: -0.0001

Data Index: 1330025 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.9597. Min Act: -0.0001

Data Index: 568834 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.9823. Min Act: -0.0001

Data Index: 455308 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.9184. Min Act: -0.0001

Data Index: 284372 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.9089. Min Act: -0.0001

Data Index: 486253 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8837. Min Act: -0.0001

Data Index: 893566 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.9058. Min Act: -0.0001

Data Index: 1358996 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8480. Min Act: -0.0001

Data Index: 728190 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8811. Min Act: -0.0001

Data Index: 221885 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8720. Min Act: -0.0001

Data Index: 8859 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8509. Min Act: -0.0001

Data Index: 985191 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8873. Min Act: -0.0001

Data Index: 119426 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8322. Min Act: -0.0001

Data Index: 595416 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.9293. Min Act: -0.0001

Data Index: 98400 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8047. Min Act: -0.0001

Data Index: 1118292 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8014. Min Act: -0.0001

Data Index: 1297804 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8460. Min Act: -0.0001

Data Index: 410728 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 1.0484. Min Range: -1.0484

Max Act: 0.8109. Min Act: -0.0001

Data Index: 22754 (C4 (Web Text))

Max Activating Token Index: 674