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

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

Neuron 3595 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.7785. Min Act: -0.0000

Data Index: 965873 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.4821. Min Act: -0.0000

Data Index: 814264 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.5548. Min Act: -0.0000

Data Index: 935365 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.5417. Min Act: -0.0000

Data Index: 781542 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.5411. Min Act: -0.0000

Data Index: 731119 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.5733. Min Act: -0.0000

Data Index: 885805 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.5721. Min Act: -0.0000

Data Index: 613810 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.4041. Min Act: -0.0000

Data Index: 1126526 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.4002. Min Act: -0.0000

Data Index: 329241 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.5687. Min Act: -0.0000

Data Index: 569001 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.4787. Min Act: -0.0000

Data Index: 446326 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.4773. Min Act: -0.0000

Data Index: 772366 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.4715. Min Act: -0.0000

Data Index: 1268647 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.4731. Min Act: -0.0000

Data Index: 257491 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.4709. Min Act: -0.0000

Data Index: 932852 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.4662. Min Act: -0.0000

Data Index: 1209104 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.3702. Min Act: -0.0000

Data Index: 95935 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.4389. Min Act: -0.0000

Data Index: 619174 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.4124. Min Act: -0.0000

Data Index: 561299 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 1.7785. Min Range: -1.7785

Max Act: 1.3213. Min Act: -0.0000

Data Index: 466779 (C4 (Web Text))

Max Activating Token Index: 591