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

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

Neuron 2314 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2503. Min Act: -0.0001

Data Index: 624528 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2490. Min Act: -0.0001

Data Index: 1038358 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2413. Min Act: -0.0000

Data Index: 460337 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2399. Min Act: 0.0000

Data Index: 945644 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2381. Min Act: -0.0001

Data Index: 178725 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2070. Min Act: -0.0001

Data Index: 1207240 (C4 (Web Text))

Max Activating Token Index: 921

Text #6

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2217. Min Act: -0.0001

Data Index: 1211680 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2219. Min Act: -0.0001

Data Index: 168632 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2224. Min Act: -0.0001

Data Index: 53929 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2412. Min Act: -0.0001

Data Index: 1280225 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2286. Min Act: -0.0000

Data Index: 1198239 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1098037 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2424. Min Act: 0.0000

Data Index: 532890 (C4 (Web Text))

Max Activating Token Index: 860

Text #13

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2265. Min Act: -0.0001

Data Index: 635606 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2310. Min Act: 0.0001

Data Index: 737418 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2313. Min Act: 0.0000

Data Index: 1172594 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2270. Min Act: -0.0001

Data Index: 1167644 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2314. Min Act: -0.0001

Data Index: 66638 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2216. Min Act: 0.0000

Data Index: 464440 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.2503. Min Range: -0.2503

Max Act: 0.2191. Min Act: -0.0001

Data Index: 100996 (C4 (Web Text))

Max Activating Token Index: 900