Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 352 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2848. Min Act: -0.0003

Data Index: 975698 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2928. Min Act: -0.0003

Data Index: 3644 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2410. Min Act: -0.0003

Data Index: 664037 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2577. Min Act: -0.0003

Data Index: 799024 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2658. Min Act: -0.0003

Data Index: 32969 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2506. Min Act: -0.0003

Data Index: 512388 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2559. Min Act: -0.0003

Data Index: 1067472 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2302. Min Act: -0.0003

Data Index: 979816 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2532. Min Act: -0.0003

Data Index: 155610 (C4 (Web Text))

Max Activating Token Index: 394

Text #9

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2272. Min Act: -0.0003

Data Index: 670063 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2421. Min Act: -0.0003

Data Index: 667739 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2307. Min Act: -0.0003

Data Index: 1246144 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2410. Min Act: -0.0003

Data Index: 548292 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2466. Min Act: -0.0003

Data Index: 1020654 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2438. Min Act: -0.0003

Data Index: 621821 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2364. Min Act: -0.0003

Data Index: 179764 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2270. Min Act: -0.0003

Data Index: 739151 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2253. Min Act: -0.0003

Data Index: 753046 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2239. Min Act: -0.0003

Data Index: 186393 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 0.2928. Min Range: -0.2928

Max Act: 0.2170. Min Act: -0.0003

Data Index: 4698 (C4 (Web Text))

Max Activating Token Index: 780