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

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

Neuron 4525 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6924. Min Range: -5.6924

Max Act: 5.6924. Min Act: -0.0000

Data Index: 73611 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 5.6924. Min Range: -5.6924

Max Act: 5.0469. Min Act: -0.0000

Data Index: 543911 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 5.6924. Min Range: -5.6924

Max Act: 5.2173. Min Act: -0.0000

Data Index: 1213659 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 5.6924. Min Range: -5.6924

Max Act: 4.8717. Min Act: -0.0000

Data Index: 1029173 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 5.6924. Min Range: -5.6924

Max Act: 4.4182. Min Act: -0.0000

Data Index: 502755 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 5.6924. Min Range: -5.6924

Max Act: 4.5540. Min Act: -0.0000

Data Index: 338362 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 5.6924. Min Range: -5.6924

Max Act: 4.2884. Min Act: -0.0000

Data Index: 552957 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 5.6924. Min Range: -5.6924

Max Act: 4.1101. Min Act: -0.0000

Data Index: 782995 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 5.6924. Min Range: -5.6924

Max Act: 3.7714. Min Act: -0.0000

Data Index: 751452 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 5.6924. Min Range: -5.6924

Max Act: 3.9375. Min Act: -0.0000

Data Index: 1143731 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 5.6924. Min Range: -5.6924

Max Act: 3.8520. Min Act: -0.0000

Data Index: 230945 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 5.6924. Min Range: -5.6924

Max Act: 3.8320. Min Act: -0.0000

Data Index: 173993 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 5.6924. Min Range: -5.6924

Max Act: 3.7458. Min Act: -0.0000

Data Index: 352909 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 5.6924. Min Range: -5.6924

Max Act: 3.5592. Min Act: -0.0000

Data Index: 13195 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 5.6924. Min Range: -5.6924

Max Act: 3.6532. Min Act: -0.0000

Data Index: 1046138 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 5.6924. Min Range: -5.6924

Max Act: 3.6685. Min Act: -0.0000

Data Index: 770662 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 5.6924. Min Range: -5.6924

Max Act: 3.4997. Min Act: -0.0000

Data Index: 668778 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 5.6924. Min Range: -5.6924

Max Act: 3.4942. Min Act: -0.0000

Data Index: 327714 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 5.6924. Min Range: -5.6924

Max Act: 3.4908. Min Act: -0.0000

Data Index: 973908 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 5.6924. Min Range: -5.6924

Max Act: 3.6225. Min Act: -0.0000

Data Index: 766863 (C4 (Web Text))

Max Activating Token Index: 137