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

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

Neuron 4310 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0532. Min Range: -1.0532

Max Act: 1.0532. Min Act: -0.0000

Data Index: 768831 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.9815. Min Act: -0.0000

Data Index: 909972 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8655. Min Act: -0.0000

Data Index: 15466 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8370. Min Act: -0.0000

Data Index: 286713 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1092666 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.8144. Min Act: -0.0000

Data Index: 663729 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7176. Min Act: -0.0000

Data Index: 243224 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7028. Min Act: -0.0000

Data Index: 4742 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7958. Min Act: -0.0000

Data Index: 949506 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7019. Min Act: -0.0000

Data Index: 949376 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7316. Min Act: -0.0000

Data Index: 722239 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7278. Min Act: -0.0000

Data Index: 317272 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7674. Min Act: -0.0000

Data Index: 650490 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1276020 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7195. Min Act: -0.0000

Data Index: 603336 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7171. Min Act: -0.0000

Data Index: 1250930 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7048. Min Act: -0.0000

Data Index: 874547 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.6893. Min Act: -0.0000

Data Index: 507066 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7071. Min Act: -0.0000

Data Index: 206362 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 1.0532. Min Range: -1.0532

Max Act: 0.7265. Min Act: -0.0000

Data Index: 513898 (C4 (Web Text))

Max Activating Token Index: 48