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

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

Neuron 3139 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.6742. Min Act: -0.0000

Data Index: 777634 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.5662. Min Act: 0.0000

Data Index: 261913 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.4675. Min Act: -0.0000

Data Index: 144602 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1224931 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.4627. Min Act: -0.0000

Data Index: 1128081 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.4062. Min Act: -0.0000

Data Index: 1331158 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.3948. Min Act: -0.0000

Data Index: 854962 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.4125. Min Act: -0.0000

Data Index: 677223 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.3741. Min Act: -0.0000

Data Index: 362250 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.3984. Min Act: -0.0000

Data Index: 1014522 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.4153. Min Act: -0.0000

Data Index: 541261 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.3817. Min Act: -0.0000

Data Index: 703626 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.3790. Min Act: -0.0000

Data Index: 87337 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.3915. Min Act: -0.0000

Data Index: 320450 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.4034. Min Act: -0.0000

Data Index: 50439 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.3989. Min Act: -0.0000

Data Index: 515955 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.3787. Min Act: -0.0000

Data Index: 429062 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.3880. Min Act: -0.0000

Data Index: 901834 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.3818. Min Act: -0.0000

Data Index: 479984 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.6742. Min Range: -0.6742

Max Act: 0.3655. Min Act: -0.0000

Data Index: 493537 (C4 (Web Text))

Max Activating Token Index: 157