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

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

Neuron 475 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1289241 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.7250. Min Act: -0.0000

Data Index: 1138978 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6434. Min Act: -0.0000

Data Index: 570721 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6102. Min Act: -0.0000

Data Index: 244795 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1326416 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1231223 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.6033. Min Act: -0.0000

Data Index: 654656 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5781. Min Act: -0.0001

Data Index: 933035 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5994. Min Act: -0.0000

Data Index: 135353 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5981. Min Act: -0.0000

Data Index: 439770 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5965. Min Act: -0.0000

Data Index: 1017603 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5775. Min Act: -0.0000

Data Index: 550128 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5950. Min Act: -0.0000

Data Index: 789426 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5562. Min Act: -0.0000

Data Index: 1115335 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5789. Min Act: -0.0000

Data Index: 889848 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5309. Min Act: -0.0000

Data Index: 724348 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1259882 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5640. Min Act: -0.0001

Data Index: 1348387 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5330. Min Act: -0.0000

Data Index: 1263983 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.7250. Min Range: -0.7250

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1132442 (C4 (Web Text))

Max Activating Token Index: 918