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

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

Neuron 920 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.8897. Min Act: -0.0001

Data Index: 471185 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.8109. Min Act: -0.0001

Data Index: 472483 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.8004. Min Act: -0.0001

Data Index: 431498 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.6637. Min Act: -0.0001

Data Index: 645003 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.6850. Min Act: -0.0001

Data Index: 888385 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.6481. Min Act: -0.0001

Data Index: 1102147 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.5603. Min Act: -0.0001

Data Index: 991061 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.6350. Min Act: -0.0001

Data Index: 226811 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.6042. Min Act: -0.0001

Data Index: 120712 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.5615. Min Act: -0.0001

Data Index: 1292672 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.5949. Min Act: -0.0001

Data Index: 756020 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.5788. Min Act: -0.0001

Data Index: 531987 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.6027. Min Act: -0.0001

Data Index: 463754 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.5753. Min Act: -0.0001

Data Index: 1333464 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.5949. Min Act: -0.0001

Data Index: 1309396 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.5689. Min Act: -0.0001

Data Index: 163332 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.5480. Min Act: -0.0001

Data Index: 593417 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.5875. Min Act: -0.0001

Data Index: 1106402 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.5656. Min Act: -0.0001

Data Index: 1249221 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.8897. Min Range: -0.8897

Max Act: 0.5860. Min Act: -0.0001

Data Index: 927349 (C4 (Web Text))

Max Activating Token Index: 701