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

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

Neuron 6101 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9176. Min Range: -2.9176

Max Act: 2.9176. Min Act: -0.0000

Data Index: 1001730 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 2.9176. Min Range: -2.9176

Max Act: 2.7564. Min Act: -0.0000

Data Index: 1272587 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 2.9176. Min Range: -2.9176

Max Act: 2.7755. Min Act: -0.0000

Data Index: 810545 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 2.9176. Min Range: -2.9176

Max Act: 2.7116. Min Act: -0.0000

Data Index: 368208 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 2.9176. Min Range: -2.9176

Max Act: 2.6968. Min Act: -0.0000

Data Index: 1111878 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 2.9176. Min Range: -2.9176

Max Act: 2.1021. Min Act: -0.0000

Data Index: 525380 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 2.9176. Min Range: -2.9176

Max Act: 2.3209. Min Act: -0.0000

Data Index: 637 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 2.9176. Min Range: -2.9176

Max Act: 2.2533. Min Act: -0.0000

Data Index: 1252973 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 2.9176. Min Range: -2.9176

Max Act: 2.4637. Min Act: -0.0000

Data Index: 101462 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 2.9176. Min Range: -2.9176

Max Act: 2.1859. Min Act: -0.0000

Data Index: 67439 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 2.9176. Min Range: -2.9176

Max Act: 2.0738. Min Act: -0.0000

Data Index: 528491 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 2.9176. Min Range: -2.9176

Max Act: 2.0231. Min Act: -0.0000

Data Index: 488746 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 2.9176. Min Range: -2.9176

Max Act: 2.1343. Min Act: -0.0000

Data Index: 82379 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 2.9176. Min Range: -2.9176

Max Act: 1.8056. Min Act: -0.0000

Data Index: 220035 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 2.9176. Min Range: -2.9176

Max Act: 2.1069. Min Act: -0.0000

Data Index: 159689 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 2.9176. Min Range: -2.9176

Max Act: 2.3403. Min Act: -0.0000

Data Index: 1005721 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 2.9176. Min Range: -2.9176

Max Act: 2.0947. Min Act: -0.0000

Data Index: 719466 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 2.9176. Min Range: -2.9176

Max Act: 2.3077. Min Act: -0.0000

Data Index: 1099980 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 2.9176. Min Range: -2.9176

Max Act: 2.2832. Min Act: -0.0000

Data Index: 1096829 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 2.9176. Min Range: -2.9176

Max Act: 1.9364. Min Act: -0.0000

Data Index: 751465 (C4 (Web Text))

Max Activating Token Index: 909