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

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

Neuron 5940 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.2907. Min Act: -0.0000

Data Index: 521870 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.2233. Min Act: -0.0000

Data Index: 574503 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.1933. Min Act: -0.0000

Data Index: 1176615 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.1834. Min Act: -0.0000

Data Index: 92248 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.1622. Min Act: -0.0000

Data Index: 277409 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.0832. Min Act: -0.0000

Data Index: 1051089 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.1886. Min Act: -0.0000

Data Index: 259141 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.1379. Min Act: -0.0000

Data Index: 686705 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.1863. Min Act: -0.0000

Data Index: 218383 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.1155. Min Act: -0.0000

Data Index: 881383 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.1157. Min Act: -0.0000

Data Index: 215295 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.0731. Min Act: -0.0000

Data Index: 513934 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.0424. Min Act: -0.0000

Data Index: 407143 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.1016. Min Act: -0.0000

Data Index: 1053794 (C4 (Web Text))

Max Activating Token Index: 447

Text #14

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.0380. Min Act: -0.0000

Data Index: 509070 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.0574. Min Act: -0.0000

Data Index: 378153 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.0995. Min Act: -0.0000

Data Index: 335737 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.1432. Min Act: -0.0000

Data Index: 445666 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.0764. Min Act: -0.0000

Data Index: 292004 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 1.2907. Min Range: -1.2907

Max Act: 1.0122. Min Act: -0.0000

Data Index: 944994 (C4 (Web Text))

Max Activating Token Index: 155