Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3405 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2662. Min Act: -0.0000

Data Index: 698295 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2472. Min Act: -0.0000

Data Index: 170284 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2531. Min Act: -0.0000

Data Index: 397225 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2475. Min Act: -0.0000

Data Index: 125583 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1084213 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2360. Min Act: -0.0000

Data Index: 869167 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2309. Min Act: -0.0000

Data Index: 175568 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1055056 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1219890 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2188. Min Act: -0.0000

Data Index: 882220 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2092. Min Act: -0.0000

Data Index: 133426 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2298. Min Act: -0.0000

Data Index: 926957 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2294. Min Act: -0.0000

Data Index: 1344584 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2203. Min Act: -0.0000

Data Index: 205590 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2169. Min Act: -0.0000

Data Index: 101101 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1062263 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2078. Min Act: -0.0000

Data Index: 527020 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2077. Min Act: -0.0000

Data Index: 625750 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2125. Min Act: -0.0000

Data Index: 165562 (C4 (Web Text))

Max Activating Token Index: 295

Text #19

Max Range: 0.2662. Min Range: -0.2662

Max Act: 0.2191. Min Act: -0.0000

Data Index: 285444 (C4 (Web Text))

Max Activating Token Index: 423