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

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

Neuron 3191 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.3024. Min Act: -0.0000

Data Index: 871203 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.2134. Min Act: -0.0000

Data Index: 980945 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1294792 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.2046. Min Act: -0.0000

Data Index: 511845 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.1700. Min Act: -0.0000

Data Index: 941937 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.1780. Min Act: -0.0000

Data Index: 1166233 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.1715. Min Act: -0.0000

Data Index: 949426 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.1711. Min Act: -0.0000

Data Index: 624663 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1187834 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.1716. Min Act: -0.0000

Data Index: 631078 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.1593. Min Act: -0.0000

Data Index: 1071197 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.1436. Min Act: -0.0000

Data Index: 1311553 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.1423. Min Act: -0.0000

Data Index: 324850 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.1525. Min Act: -0.0000

Data Index: 734214 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.1531. Min Act: -0.0000

Data Index: 548133 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.1444. Min Act: -0.0000

Data Index: 144420 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.1380. Min Act: -0.0000

Data Index: 581576 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.1452. Min Act: -0.0000

Data Index: 694521 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.1375. Min Act: -0.0000

Data Index: 542945 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.3024. Min Range: -0.3024

Max Act: 0.1417. Min Act: -0.0000

Data Index: 126428 (C4 (Web Text))

Max Activating Token Index: 210