Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1619 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.7764. Min Act: -0.0000

Data Index: 883409 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.8012. Min Act: -0.0000

Data Index: 114142 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1331313 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.7706. Min Act: -0.0000

Data Index: 531669 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.7869. Min Act: -0.0000

Data Index: 84196 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.7177. Min Act: -0.0000

Data Index: 692577 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.7383. Min Act: -0.0000

Data Index: 510129 (C4 (Web Text))

Max Activating Token Index: 668

Text #7

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6995. Min Act: -0.0000

Data Index: 56041 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1200572 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6597. Min Act: -0.0000

Data Index: 909562 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6796. Min Act: -0.0000

Data Index: 463353 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6472. Min Act: -0.0000

Data Index: 430235 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6590. Min Act: -0.0000

Data Index: 124069 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6396. Min Act: -0.0000

Data Index: 792812 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6449. Min Act: -0.0000

Data Index: 905524 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6545. Min Act: -0.0000

Data Index: 432404 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1320722 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6460. Min Act: -0.0000

Data Index: 318622 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6400. Min Act: -0.0000

Data Index: 536579 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.8012. Min Range: -0.8012

Max Act: 0.6387. Min Act: -0.0000

Data Index: 320444 (C4 (Web Text))

Max Activating Token Index: 1022