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

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

Neuron 438 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4132. Min Range: -1.4132

Max Act: 1.4132. Min Act: -0.0000

Data Index: 511091 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 1.4132. Min Range: -1.4132

Max Act: 1.1156. Min Act: -0.0000

Data Index: 614549 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 1.4132. Min Range: -1.4132

Max Act: 1.2611. Min Act: -0.0000

Data Index: 459715 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 1.4132. Min Range: -1.4132

Max Act: 1.0801. Min Act: -0.0000

Data Index: 905270 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 1.4132. Min Range: -1.4132

Max Act: 1.1357. Min Act: -0.0000

Data Index: 784687 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 1.4132. Min Range: -1.4132

Max Act: 1.1359. Min Act: -0.0000

Data Index: 901197 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 1.4132. Min Range: -1.4132

Max Act: 1.0729. Min Act: -0.0000

Data Index: 27010 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 1.4132. Min Range: -1.4132

Max Act: 0.9776. Min Act: -0.0000

Data Index: 771385 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 1.4132. Min Range: -1.4132

Max Act: 0.9965. Min Act: -0.0000

Data Index: 75728 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 1.4132. Min Range: -1.4132

Max Act: 1.0695. Min Act: -0.0000

Data Index: 311023 (C4 (Web Text))

Max Activating Token Index: 941

Text #10

Max Range: 1.4132. Min Range: -1.4132

Max Act: 1.0707. Min Act: -0.0000

Data Index: 148495 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 1.4132. Min Range: -1.4132

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1470395 (Python Code)

Max Activating Token Index: 670

Text #12

Max Range: 1.4132. Min Range: -1.4132

Max Act: 1.0935. Min Act: -0.0000

Data Index: 319955 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 1.4132. Min Range: -1.4132

Max Act: 0.9043. Min Act: -0.0000

Data Index: 1087368 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 1.4132. Min Range: -1.4132

Max Act: 0.9200. Min Act: -0.0000

Data Index: 598489 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 1.4132. Min Range: -1.4132

Max Act: 0.8949. Min Act: -0.0000

Data Index: 180224 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 1.4132. Min Range: -1.4132

Max Act: 0.9080. Min Act: -0.0000

Data Index: 64267 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 1.4132. Min Range: -1.4132

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1646073 (Python Code)

Max Activating Token Index: 109

Text #18

Max Range: 1.4132. Min Range: -1.4132

Max Act: 0.9721. Min Act: -0.0000

Data Index: 154362 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 1.4132. Min Range: -1.4132

Max Act: 0.9242. Min Act: -0.0000

Data Index: 623342 (C4 (Web Text))

Max Activating Token Index: 632