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

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

Neuron 4594 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8545. Min Range: -4.8545

Max Act: 4.8545. Min Act: -0.0000

Data Index: 770773 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 4.8545. Min Range: -4.8545

Max Act: 4.3350. Min Act: -0.0000

Data Index: 1019009 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 4.8545. Min Range: -4.8545

Max Act: 4.3861. Min Act: -0.0000

Data Index: 734059 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 4.8545. Min Range: -4.8545

Max Act: 4.6460. Min Act: -0.0000

Data Index: 522827 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 4.8545. Min Range: -4.8545

Max Act: 4.1239. Min Act: -0.0000

Data Index: 749603 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 4.8545. Min Range: -4.8545

Max Act: 3.9644. Min Act: -0.0000

Data Index: 88937 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 4.8545. Min Range: -4.8545

Max Act: 4.1423. Min Act: -0.0000

Data Index: 190476 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 4.8545. Min Range: -4.8545

Max Act: 3.8642. Min Act: -0.0000

Data Index: 835841 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 4.8545. Min Range: -4.8545

Max Act: 3.9931. Min Act: -0.0000

Data Index: 762393 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 4.8545. Min Range: -4.8545

Max Act: 3.8714. Min Act: -0.0000

Data Index: 893086 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 4.8545. Min Range: -4.8545

Max Act: 4.0116. Min Act: -0.0000

Data Index: 338106 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 4.8545. Min Range: -4.8545

Max Act: 3.8235. Min Act: -0.0000

Data Index: 509319 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 4.8545. Min Range: -4.8545

Max Act: 3.9657. Min Act: -0.0000

Data Index: 264959 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 4.8545. Min Range: -4.8545

Max Act: 3.6815. Min Act: -0.0000

Data Index: 944783 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 4.8545. Min Range: -4.8545

Max Act: 3.9502. Min Act: -0.0000

Data Index: 398038 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 4.8545. Min Range: -4.8545

Max Act: 3.8295. Min Act: -0.0000

Data Index: 40682 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 4.8545. Min Range: -4.8545

Max Act: 3.3564. Min Act: -0.0000

Data Index: 1250656 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 4.8545. Min Range: -4.8545

Max Act: 3.6106. Min Act: -0.0000

Data Index: 328923 (C4 (Web Text))

Max Activating Token Index: 651

Text #18

Max Range: 4.8545. Min Range: -4.8545

Max Act: 3.4965. Min Act: -0.0000

Data Index: 555794 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 4.8545. Min Range: -4.8545

Max Act: 3.3620. Min Act: -0.0000

Data Index: 687114 (C4 (Web Text))

Max Activating Token Index: 816