Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 259 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6952. Min Act: -0.0001

Data Index: 555201 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.7083. Min Act: -0.0002

Data Index: 964548 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6559. Min Act: -0.0002

Data Index: 1323427 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6687. Min Act: -0.0001

Data Index: 828086 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6602. Min Act: -0.0001

Data Index: 1038502 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.7003. Min Act: -0.0002

Data Index: 1008934 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.7051. Min Act: -0.0002

Data Index: 298388 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.7023. Min Act: -0.0002

Data Index: 1046939 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6517. Min Act: -0.0001

Data Index: 316865 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6348. Min Act: -0.0002

Data Index: 355611 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6626. Min Act: -0.0002

Data Index: 1266635 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6797. Min Act: -0.0002

Data Index: 1349108 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6387. Min Act: -0.0001

Data Index: 665560 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6336. Min Act: -0.0001

Data Index: 1213028 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6712. Min Act: -0.0001

Data Index: 1255853 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6533. Min Act: -0.0002

Data Index: 690402 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6268. Min Act: -0.0002

Data Index: 1286975 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6418. Min Act: -0.0001

Data Index: 361991 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6865. Min Act: -0.0001

Data Index: 903764 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 0.7083. Min Range: -0.7083

Max Act: 0.6387. Min Act: -0.0002

Data Index: 601670 (C4 (Web Text))

Max Activating Token Index: 689