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

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

Neuron 800 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.9842. Min Act: -0.0000

Data Index: 20351 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 1.0003. Min Range: -1.0003

Max Act: 1.0003. Min Act: -0.0000

Data Index: 1293969 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8948. Min Act: -0.0000

Data Index: 129063 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8657. Min Act: -0.0000

Data Index: 133721 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8758. Min Act: -0.0000

Data Index: 665145 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8337. Min Act: -0.0000

Data Index: 58752 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8493. Min Act: -0.0000

Data Index: 444587 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7981. Min Act: -0.0000

Data Index: 583112 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8565. Min Act: -0.0000

Data Index: 1554733 (Python Code)

Max Activating Token Index: 941

Text #9

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8505. Min Act: -0.0000

Data Index: 1124717 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8160. Min Act: -0.0000

Data Index: 658371 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8160. Min Act: -0.0000

Data Index: 767514 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8101. Min Act: -0.0000

Data Index: 153362 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7936. Min Act: -0.0000

Data Index: 266800 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7967. Min Act: -0.0000

Data Index: 724525 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7800. Min Act: -0.0000

Data Index: 849043 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7630. Min Act: -0.0000

Data Index: 19530 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7700. Min Act: -0.0000

Data Index: 692997 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1388442 (Python Code)

Max Activating Token Index: 723

Text #19

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7888. Min Act: -0.0000

Data Index: 37942 (C4 (Web Text))

Max Activating Token Index: 846