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

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

Neuron 1347 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.9914. Min Act: -0.0002

Data Index: 133875 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8535. Min Act: -0.0002

Data Index: 805976 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.9980. Min Act: -0.0002

Data Index: 799321 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8968. Min Act: -0.0002

Data Index: 961162 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.9459. Min Act: -0.0002

Data Index: 1267049 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.9744. Min Act: -0.0002

Data Index: 700744 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8799. Min Act: -0.0002

Data Index: 567895 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8924. Min Act: -0.0002

Data Index: 592021 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8886. Min Act: -0.0002

Data Index: 1125912 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8817. Min Act: -0.0002

Data Index: 196701 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8547. Min Act: -0.0002

Data Index: 848115 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8972. Min Act: -0.0002

Data Index: 525387 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8325. Min Act: -0.0002

Data Index: 756721 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.9015. Min Act: -0.0002

Data Index: 129913 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8658. Min Act: -0.0002

Data Index: 1202999 (C4 (Web Text))

Max Activating Token Index: 585

Text #15

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8466. Min Act: -0.0002

Data Index: 126320 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7400. Min Act: -0.0002

Data Index: 667677 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8399. Min Act: -0.0002

Data Index: 817971 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.8071. Min Act: -0.0002

Data Index: 805375 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.9980. Min Range: -0.9980

Max Act: 0.7808. Min Act: -0.0002

Data Index: 761883 (C4 (Web Text))

Max Activating Token Index: 805