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

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

Neuron 4604 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0984. Min Range: -4.0984

Max Act: 4.0984. Min Act: -0.0000

Data Index: 497050 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 4.0984. Min Range: -4.0984

Max Act: 3.4462. Min Act: -0.0000

Data Index: 369250 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 4.0984. Min Range: -4.0984

Max Act: 3.1279. Min Act: -0.0000

Data Index: 161639 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 4.0984. Min Range: -4.0984

Max Act: 3.1991. Min Act: -0.0000

Data Index: 1120573 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 4.0984. Min Range: -4.0984

Max Act: 3.1174. Min Act: -0.0000

Data Index: 658289 (C4 (Web Text))

Max Activating Token Index: 994

Text #5

Max Range: 4.0984. Min Range: -4.0984

Max Act: 2.8504. Min Act: -0.0000

Data Index: 291359 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 4.0984. Min Range: -4.0984

Max Act: 2.7353. Min Act: -0.0000

Data Index: 203912 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 4.0984. Min Range: -4.0984

Max Act: 2.8651. Min Act: -0.0000

Data Index: 1278988 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 4.0984. Min Range: -4.0984

Max Act: 2.5430. Min Act: -0.0000

Data Index: 878703 (C4 (Web Text))

Max Activating Token Index: 256

Text #9

Max Range: 4.0984. Min Range: -4.0984

Max Act: 2.5186. Min Act: -0.0000

Data Index: 780709 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 4.0984. Min Range: -4.0984

Max Act: 2.7880. Min Act: -0.0000

Data Index: 28699 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 4.0984. Min Range: -4.0984

Max Act: 2.7802. Min Act: -0.0000

Data Index: 169859 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 4.0984. Min Range: -4.0984

Max Act: 2.6005. Min Act: -0.0000

Data Index: 478851 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 4.0984. Min Range: -4.0984

Max Act: 2.5879. Min Act: -0.0000

Data Index: 1224703 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 4.0984. Min Range: -4.0984

Max Act: 2.4469. Min Act: -0.0000

Data Index: 1213427 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 4.0984. Min Range: -4.0984

Max Act: 2.5513. Min Act: -0.0000

Data Index: 781264 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 4.0984. Min Range: -4.0984

Max Act: 2.5516. Min Act: -0.0000

Data Index: 512348 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 4.0984. Min Range: -4.0984

Max Act: 2.3898. Min Act: -0.0000

Data Index: 1006132 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 4.0984. Min Range: -4.0984

Max Act: 2.7937. Min Act: -0.0000

Data Index: 1224835 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 4.0984. Min Range: -4.0984

Max Act: 2.3829. Min Act: -0.0000

Data Index: 142040 (C4 (Web Text))

Max Activating Token Index: 898