Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3403 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2823. Min Act: -0.0000

Data Index: 1256522 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2115. Min Act: -0.0000

Data Index: 1107449 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2207. Min Act: -0.0000

Data Index: 1185208 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2145. Min Act: -0.0000

Data Index: 337627 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2152. Min Act: -0.0000

Data Index: 271451 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1905. Min Act: -0.0000

Data Index: 897666 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1878. Min Act: -0.0000

Data Index: 338410 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1886. Min Act: -0.0000

Data Index: 427455 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1114536 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1830. Min Act: -0.0000

Data Index: 659661 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1726. Min Act: -0.0000

Data Index: 883493 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1981. Min Act: -0.0000

Data Index: 395104 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1909. Min Act: -0.0000

Data Index: 1292144 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1789. Min Act: -0.0000

Data Index: 830707 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1644. Min Act: -0.0000

Data Index: 712906 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1717. Min Act: -0.0000

Data Index: 595634 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1680. Min Act: -0.0000

Data Index: 900253 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1592. Min Act: -0.0000

Data Index: 244639 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1548. Min Act: -0.0000

Data Index: 517515 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.2823. Min Range: -0.2823

Max Act: 0.1542. Min Act: -0.0000

Data Index: 958841 (C4 (Web Text))

Max Activating Token Index: 941