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

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

Neuron 3907 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.1024. Min Act: -0.0002

Data Index: 753342 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.1041. Min Act: -0.0002

Data Index: 819654 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.1059. Min Act: -0.0002

Data Index: 285045 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.1091. Min Act: -0.0002

Data Index: 380715 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0979. Min Act: -0.0002

Data Index: 114522 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0971. Min Act: -0.0002

Data Index: 678031 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1338674 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1026209 (C4 (Web Text))

Max Activating Token Index: 336

Text #8

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0920. Min Act: -0.0002

Data Index: 91773 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0841. Min Act: -0.0002

Data Index: 438447 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0938. Min Act: -0.0002

Data Index: 1124427 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0859. Min Act: -0.0002

Data Index: 687327 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0940. Min Act: -0.0002

Data Index: 458706 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0893. Min Act: -0.0002

Data Index: 185152 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0769. Min Act: -0.0002

Data Index: 810514 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1139553 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1081447 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0826. Min Act: -0.0002

Data Index: 459532 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0834. Min Act: -0.0002

Data Index: 498387 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.1091. Min Range: -0.1091

Max Act: 0.0819. Min Act: -0.0002

Data Index: 686854 (C4 (Web Text))

Max Activating Token Index: 627