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

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

Neuron 1597 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.6693. Min Act: -0.0000

Data Index: 726558 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.6617. Min Act: -0.0000

Data Index: 1200841 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.6535. Min Act: -0.0000

Data Index: 852142 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.6249. Min Act: -0.0000

Data Index: 736231 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.6192. Min Act: -0.0000

Data Index: 289817 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.5721. Min Act: -0.0000

Data Index: 368236 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.5418. Min Act: -0.0000

Data Index: 373665 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.5695. Min Act: -0.0000

Data Index: 522276 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.5572. Min Act: -0.0000

Data Index: 674801 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1135023 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.5919. Min Act: -0.0000

Data Index: 546652 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.5347. Min Act: -0.0000

Data Index: 362343 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.5575. Min Act: -0.0000

Data Index: 477168 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.5486. Min Act: -0.0000

Data Index: 124142 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1073235 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.5460. Min Act: -0.0000

Data Index: 617191 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.5449. Min Act: -0.0000

Data Index: 160670 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.5405. Min Act: -0.0000

Data Index: 758277 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.5390. Min Act: -0.0000

Data Index: 369011 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.6693. Min Range: -0.6693

Max Act: 0.5371. Min Act: -0.0000

Data Index: 856578 (C4 (Web Text))

Max Activating Token Index: 64