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

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

Neuron 4918 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1352065 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.6842. Min Act: -0.0000

Data Index: 216817 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.6374. Min Act: -0.0000

Data Index: 1267920 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.6585. Min Act: -0.0000

Data Index: 488166 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.6617. Min Act: -0.0000

Data Index: 309683 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.6172. Min Act: -0.0000

Data Index: 1077273 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.5827. Min Act: -0.0000

Data Index: 425385 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1017360 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.5992. Min Act: -0.0000

Data Index: 698378 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.5838. Min Act: -0.0000

Data Index: 746686 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.5504. Min Act: -0.0000

Data Index: 566086 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1322562 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1074 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.5517. Min Act: -0.0000

Data Index: 740077 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.5409. Min Act: -0.0000

Data Index: 350611 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.5390. Min Act: -0.0000

Data Index: 319517 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.5032. Min Act: -0.0000

Data Index: 299599 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.5272. Min Act: -0.0000

Data Index: 816214 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.5738. Min Act: -0.0000

Data Index: 395868 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.8584. Min Range: -0.8584

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1068280 (C4 (Web Text))

Max Activating Token Index: 841