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

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

Neuron 1814 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.3013. Min Act: -0.0000

Data Index: 871986 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.2702. Min Act: -0.0000

Data Index: 1209958 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.2686. Min Act: -0.0000

Data Index: 897669 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.2505. Min Act: -0.0000

Data Index: 552945 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.2076. Min Act: -0.0000

Data Index: 882448 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.2191. Min Act: -0.0000

Data Index: 628802 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1240882 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.1969. Min Act: -0.0000

Data Index: 93294 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.2028. Min Act: -0.0000

Data Index: 229231 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.2026. Min Act: -0.0000

Data Index: 1202792 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1345148 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.1979. Min Act: -0.0000

Data Index: 620882 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.1869. Min Act: -0.0000

Data Index: 842031 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.1933. Min Act: -0.0000

Data Index: 264483 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.1909. Min Act: -0.0000

Data Index: 1114724 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.1897. Min Act: -0.0000

Data Index: 929516 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.1896. Min Act: -0.0000

Data Index: 1133076 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.1948. Min Act: -0.0000

Data Index: 143182 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.1865. Min Act: -0.0000

Data Index: 1240568 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.3013. Min Range: -0.3013

Max Act: 0.1924. Min Act: -0.0000

Data Index: 758640 (C4 (Web Text))

Max Activating Token Index: 210