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

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

Neuron 2019 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6441. Min Range: -2.6441

Max Act: 2.6441. Min Act: -0.0000

Data Index: 119159 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 2.6441. Min Range: -2.6441

Max Act: 2.0826. Min Act: -0.0000

Data Index: 439575 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 2.6441. Min Range: -2.6441

Max Act: 1.7287. Min Act: -0.0000

Data Index: 251651 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 2.6441. Min Range: -2.6441

Max Act: 1.4824. Min Act: -0.0000

Data Index: 1226322 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 2.6441. Min Range: -2.6441

Max Act: 1.4458. Min Act: -0.0000

Data Index: 304507 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 2.6441. Min Range: -2.6441

Max Act: 1.5470. Min Act: -0.0000

Data Index: 845798 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 2.6441. Min Range: -2.6441

Max Act: 1.5235. Min Act: -0.0000

Data Index: 1231984 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 2.6441. Min Range: -2.6441

Max Act: 1.5791. Min Act: -0.0000

Data Index: 839663 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 2.6441. Min Range: -2.6441

Max Act: 1.5749. Min Act: -0.0000

Data Index: 135126 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 2.6441. Min Range: -2.6441

Max Act: 1.3600. Min Act: -0.0000

Data Index: 719585 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 2.6441. Min Range: -2.6441

Max Act: 1.4424. Min Act: -0.0000

Data Index: 409699 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 2.6441. Min Range: -2.6441

Max Act: 1.4343. Min Act: -0.0000

Data Index: 695769 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 2.6441. Min Range: -2.6441

Max Act: 1.5249. Min Act: -0.0000

Data Index: 727484 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 2.6441. Min Range: -2.6441

Max Act: 1.3379. Min Act: -0.0000

Data Index: 1267992 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 2.6441. Min Range: -2.6441

Max Act: 1.3267. Min Act: -0.0000

Data Index: 1343149 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 2.6441. Min Range: -2.6441

Max Act: 1.4934. Min Act: -0.0000

Data Index: 112213 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 2.6441. Min Range: -2.6441

Max Act: 1.3952. Min Act: -0.0000

Data Index: 150149 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 2.6441. Min Range: -2.6441

Max Act: 1.4581. Min Act: -0.0000

Data Index: 759610 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 2.6441. Min Range: -2.6441

Max Act: 1.3126. Min Act: -0.0000

Data Index: 883775 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 2.6441. Min Range: -2.6441

Max Act: 1.3535. Min Act: -0.0000

Data Index: 689044 (C4 (Web Text))

Max Activating Token Index: 233