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

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

Neuron 2184 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: 6.9721. Min Range: -6.9721

Max Act: 6.9721. Min Act: -0.0000

Data Index: 859630 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 6.9721. Min Range: -6.9721

Max Act: 6.5861. Min Act: -0.0000

Data Index: 425237 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 6.9721. Min Range: -6.9721

Max Act: 6.5932. Min Act: -0.0000

Data Index: 94611 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 6.9721. Min Range: -6.9721

Max Act: 6.5601. Min Act: -0.0000

Data Index: 1051597 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 6.9721. Min Range: -6.9721

Max Act: 6.7971. Min Act: -0.0000

Data Index: 899430 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 6.9721. Min Range: -6.9721

Max Act: 6.0861. Min Act: -0.0000

Data Index: 1044486 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 6.9721. Min Range: -6.9721

Max Act: 6.2710. Min Act: -0.0000

Data Index: 589975 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 6.9721. Min Range: -6.9721

Max Act: 6.2459. Min Act: -0.0000

Data Index: 854785 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 6.9721. Min Range: -6.9721

Max Act: 6.2341. Min Act: -0.0000

Data Index: 97121 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 6.9721. Min Range: -6.9721

Max Act: 6.2361. Min Act: -0.0000

Data Index: 39708 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 6.9721. Min Range: -6.9721

Max Act: 6.2219. Min Act: -0.0000

Data Index: 475404 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 6.9721. Min Range: -6.9721

Max Act: 6.2216. Min Act: -0.0000

Data Index: 694656 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 6.9721. Min Range: -6.9721

Max Act: 6.4193. Min Act: -0.0000

Data Index: 1203001 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 6.9721. Min Range: -6.9721

Max Act: 6.2161. Min Act: -0.0000

Data Index: 624099 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 6.9721. Min Range: -6.9721

Max Act: 6.0335. Min Act: -0.0000

Data Index: 779988 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 6.9721. Min Range: -6.9721

Max Act: 5.9894. Min Act: -0.0000

Data Index: 440892 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 6.9721. Min Range: -6.9721

Max Act: 5.7394. Min Act: -0.0000

Data Index: 1024788 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 6.9721. Min Range: -6.9721

Max Act: 5.9164. Min Act: -0.0000

Data Index: 924738 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 6.9721. Min Range: -6.9721

Max Act: 6.1005. Min Act: -0.0000

Data Index: 104623 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 6.9721. Min Range: -6.9721

Max Act: 5.8990. Min Act: -0.0000

Data Index: 518099 (C4 (Web Text))

Max Activating Token Index: 236