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

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

Neuron 3489 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: 0.8874. Min Range: -0.8874

Max Act: 0.8874. Min Act: -0.0001

Data Index: 84146 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.8867. Min Act: -0.0001

Data Index: 1348643 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.8479. Min Act: -0.0001

Data Index: 67735 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.8414. Min Act: -0.0001

Data Index: 588108 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.8118. Min Act: -0.0001

Data Index: 239793 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.8775. Min Act: -0.0001

Data Index: 1312907 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.7711. Min Act: -0.0001

Data Index: 879295 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.7607. Min Act: -0.0001

Data Index: 353057 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.7571. Min Act: -0.0001

Data Index: 663739 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.8279. Min Act: -0.0002

Data Index: 1298284 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.7275. Min Act: -0.0002

Data Index: 1350373 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.7283. Min Act: -0.0001

Data Index: 1228328 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.7319. Min Act: -0.0002

Data Index: 547824 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6901. Min Act: -0.0001

Data Index: 1016320 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6900. Min Act: -0.0001

Data Index: 1648447 (Python Code)

Max Activating Token Index: 750

Text #15

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.7362. Min Act: -0.0002

Data Index: 804314 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6922. Min Act: -0.0001

Data Index: 481566 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.6827. Min Act: -0.0001

Data Index: 574534 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.7034. Min Act: -0.0002

Data Index: 197376 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 0.8874. Min Range: -0.8874

Max Act: 0.7269. Min Act: -0.0001

Data Index: 740747 (C4 (Web Text))

Max Activating Token Index: 419