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

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

Neuron 500 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.3285. Min Act: -0.0002

Data Index: 220752 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.2835. Min Act: -0.0002

Data Index: 223686 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.0294. Min Act: -0.0002

Data Index: 175080 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.0655. Min Act: -0.0002

Data Index: 450431 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.8754. Min Act: -0.0002

Data Index: 1281143 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9288. Min Act: -0.0002

Data Index: 1056035 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 1.3285. Min Range: -1.3285

Max Act: 1.0056. Min Act: -0.0002

Data Index: 1141960 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9143. Min Act: -0.0002

Data Index: 110599 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9622. Min Act: -0.0002

Data Index: 683975 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9901. Min Act: -0.0002

Data Index: 1020494 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9269. Min Act: -0.0002

Data Index: 1056553 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9240. Min Act: -0.0002

Data Index: 1059510 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9223. Min Act: -0.0002

Data Index: 299420 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9272. Min Act: -0.0001

Data Index: 1284083 (C4 (Web Text))

Max Activating Token Index: 1002

Text #14

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9701. Min Act: -0.0001

Data Index: 476336 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9448. Min Act: -0.0001

Data Index: 434463 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9166. Min Act: -0.0002

Data Index: 778421 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.9046. Min Act: -0.0002

Data Index: 8903 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.8452. Min Act: -0.0002

Data Index: 229178 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 1.3285. Min Range: -1.3285

Max Act: 0.8322. Min Act: -0.0002

Data Index: 517762 (C4 (Web Text))

Max Activating Token Index: 632