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

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

Neuron 2553 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: 2.2731. Min Range: -2.2731

Max Act: 2.2731. Min Act: -0.0000

Data Index: 948579 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 2.2731. Min Range: -2.2731

Max Act: 2.1678. Min Act: -0.0000

Data Index: 90945 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 2.2731. Min Range: -2.2731

Max Act: 2.1501. Min Act: -0.0000

Data Index: 1528784 (Python Code)

Max Activating Token Index: 390

Text #3

Max Range: 2.2731. Min Range: -2.2731

Max Act: 1.9921. Min Act: -0.0000

Data Index: 1265738 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 2.2731. Min Range: -2.2731

Max Act: 1.8959. Min Act: -0.0000

Data Index: 1032385 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 2.2731. Min Range: -2.2731

Max Act: 1.9999. Min Act: -0.0000

Data Index: 1112515 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 2.2731. Min Range: -2.2731

Max Act: 1.8665. Min Act: -0.0000

Data Index: 754700 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 2.2731. Min Range: -2.2731

Max Act: 1.9740. Min Act: -0.0000

Data Index: 107103 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 2.2731. Min Range: -2.2731

Max Act: 1.9506. Min Act: -0.0000

Data Index: 1154951 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 2.2731. Min Range: -2.2731

Max Act: 1.9241. Min Act: -0.0000

Data Index: 393532 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 2.2731. Min Range: -2.2731

Max Act: 1.9146. Min Act: -0.0000

Data Index: 419822 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 2.2731. Min Range: -2.2731

Max Act: 1.7862. Min Act: -0.0000

Data Index: 705363 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 2.2731. Min Range: -2.2731

Max Act: 1.8895. Min Act: -0.0000

Data Index: 1278205 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 2.2731. Min Range: -2.2731

Max Act: 1.8069. Min Act: -0.0000

Data Index: 652510 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 2.2731. Min Range: -2.2731

Max Act: 1.9094. Min Act: -0.0000

Data Index: 1450965 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 2.2731. Min Range: -2.2731

Max Act: 1.7972. Min Act: -0.0000

Data Index: 469694 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 2.2731. Min Range: -2.2731

Max Act: 1.7848. Min Act: -0.0000

Data Index: 1625457 (Python Code)

Max Activating Token Index: 291

Text #17

Max Range: 2.2731. Min Range: -2.2731

Max Act: 1.7828. Min Act: -0.0000

Data Index: 688001 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 2.2731. Min Range: -2.2731

Max Act: 1.7719. Min Act: -0.0000

Data Index: 290856 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 2.2731. Min Range: -2.2731

Max Act: 1.7697. Min Act: -0.0000

Data Index: 289383 (C4 (Web Text))

Max Activating Token Index: 791