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

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

Neuron 5763 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1488224 (Python Code)

Max Activating Token Index: 924

Text #1

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.1009. Min Act: -0.0001

Data Index: 248151 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0986. Min Act: -0.0001

Data Index: 372366 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1071614 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0968. Min Act: -0.0001

Data Index: 631858 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0895. Min Act: -0.0001

Data Index: 186932 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0930. Min Act: -0.0001

Data Index: 949976 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0945. Min Act: -0.0001

Data Index: 1514212 (Python Code)

Max Activating Token Index: 161

Text #8

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1477 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0940. Min Act: -0.0001

Data Index: 1083619 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0819. Min Act: -0.0001

Data Index: 1356320 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0861. Min Act: -0.0001

Data Index: 30337 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0984. Min Act: -0.0001

Data Index: 815007 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0884. Min Act: -0.0001

Data Index: 1616998 (Python Code)

Max Activating Token Index: 547

Text #14

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0820. Min Act: -0.0001

Data Index: 423141 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0862. Min Act: -0.0001

Data Index: 624775 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0892. Min Act: -0.0001

Data Index: 1378319 (Python Code)

Max Activating Token Index: 474

Text #17

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0789. Min Act: -0.0001

Data Index: 659527 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1123099 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.1085. Min Range: -0.1085

Max Act: 0.0926. Min Act: -0.0001

Data Index: 336611 (C4 (Web Text))

Max Activating Token Index: 154