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

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

Neuron 1990 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: 0.0303. Min Range: -0.0303

Max Act: 0.0303. Min Act: -0.0003

Data Index: 645546 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1347043 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0276. Min Act: -0.0003

Data Index: 668572 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0268. Min Act: -0.0003

Data Index: 1643786 (Python Code)

Max Activating Token Index: 55

Text #4

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0276. Min Act: -0.0003

Data Index: 391526 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0275. Min Act: -0.0003

Data Index: 1470372 (Python Code)

Max Activating Token Index: 71

Text #6

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1553263 (Python Code)

Max Activating Token Index: 215

Text #7

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1025268 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0263. Min Act: -0.0003

Data Index: 199740 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0245. Min Act: -0.0003

Data Index: 1599050 (Python Code)

Max Activating Token Index: 206

Text #10

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0278. Min Act: -0.0003

Data Index: 1532667 (Python Code)

Max Activating Token Index: 284

Text #11

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0257. Min Act: -0.0003

Data Index: 903260 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0262. Min Act: -0.0003

Data Index: 384956 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1094482 (C4 (Web Text))

Max Activating Token Index: 695

Text #14

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1385783 (Python Code)

Max Activating Token Index: 314

Text #15

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0276. Min Act: -0.0003

Data Index: 770447 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1456960 (Python Code)

Max Activating Token Index: 641

Text #17

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1585344 (Python Code)

Max Activating Token Index: 712

Text #18

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0250. Min Act: -0.0003

Data Index: 130644 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0254. Min Act: -0.0003

Data Index: 968562 (C4 (Web Text))

Max Activating Token Index: 169