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

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

Neuron 1651 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.5806. Min Act: -0.0001

Data Index: 217636 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.5500. Min Act: -0.0001

Data Index: 965689 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.6015. Min Act: -0.0001

Data Index: 774379 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.5250. Min Act: -0.0001

Data Index: 537523 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.5225. Min Act: -0.0001

Data Index: 1161026 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.5803. Min Act: -0.0001

Data Index: 92541 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.5354. Min Act: -0.0001

Data Index: 1054383 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.5224. Min Act: -0.0001

Data Index: 777754 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.5514. Min Act: -0.0001

Data Index: 607921 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.5006. Min Act: -0.0001

Data Index: 182782 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.5260. Min Act: -0.0001

Data Index: 499484 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.4949. Min Act: -0.0001

Data Index: 219597 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.5359. Min Act: -0.0001

Data Index: 1204842 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.5569. Min Act: -0.0001

Data Index: 101978 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.4870. Min Act: -0.0001

Data Index: 998805 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.4962. Min Act: -0.0001

Data Index: 415550 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.5831. Min Act: -0.0001

Data Index: 482554 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.4495. Min Act: -0.0001

Data Index: 603404 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.4339. Min Act: -0.0001

Data Index: 565123 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.6015. Min Range: -0.6015

Max Act: 0.5167. Min Act: -0.0001

Data Index: 653979 (C4 (Web Text))

Max Activating Token Index: 255