Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2552 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.9653. Min Act: -0.0001

Data Index: 223068 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.9097. Min Act: -0.0000

Data Index: 940620 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.9347. Min Act: -0.0000

Data Index: 836046 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.9444. Min Act: -0.0001

Data Index: 920375 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.9515. Min Act: -0.0000

Data Index: 1064941 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.8585. Min Act: -0.0000

Data Index: 773087 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.8504. Min Act: -0.0001

Data Index: 587065 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.8780. Min Act: -0.0000

Data Index: 1171343 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.8020. Min Act: -0.0001

Data Index: 327090 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.9433. Min Act: -0.0001

Data Index: 1123327 (C4 (Web Text))

Max Activating Token Index: 914

Text #10

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.8540. Min Act: -0.0000

Data Index: 582219 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.8398. Min Act: -0.0000

Data Index: 513825 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.8351. Min Act: -0.0000

Data Index: 1226043 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.8067. Min Act: -0.0001

Data Index: 763408 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.8249. Min Act: -0.0000

Data Index: 536890 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.9590. Min Act: -0.0000

Data Index: 471874 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.8155. Min Act: -0.0001

Data Index: 279658 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.8177. Min Act: -0.0001

Data Index: 1197051 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.8540. Min Act: -0.0000

Data Index: 186274 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.9653. Min Range: -0.9653

Max Act: 0.9089. Min Act: -0.0000

Data Index: 412948 (C4 (Web Text))

Max Activating Token Index: 472