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

Dataset: The Pile

Neuron 1120 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3340. Min Act: -0.0000

Data Index: 1061827 (The Pile)

Max Activating Token Index: 388

Text #1

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1995222 (The Pile)

Max Activating Token Index: 428

Text #2

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2838. Min Act: -0.0000

Data Index: 1837383 (The Pile)

Max Activating Token Index: 107

Text #3

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2774. Min Act: -0.0000

Data Index: 1152576 (The Pile)

Max Activating Token Index: 297

Text #4

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2835. Min Act: -0.0000

Data Index: 555766 (The Pile)

Max Activating Token Index: 917

Text #5

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1498667 (The Pile)

Max Activating Token Index: 733

Text #6

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1483234 (The Pile)

Max Activating Token Index: 189

Text #7

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2649. Min Act: -0.0000

Data Index: 1719489 (The Pile)

Max Activating Token Index: 408

Text #8

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1968668 (The Pile)

Max Activating Token Index: 63

Text #9

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1850602 (The Pile)

Max Activating Token Index: 700

Text #10

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2258. Min Act: -0.0000

Data Index: 598912 (The Pile)

Max Activating Token Index: 268

Text #11

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2488. Min Act: -0.0000

Data Index: 1946322 (The Pile)

Max Activating Token Index: 453

Text #12

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2216. Min Act: -0.0000

Data Index: 725059 (The Pile)

Max Activating Token Index: 194

Text #13

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2222. Min Act: -0.0000

Data Index: 1362444 (The Pile)

Max Activating Token Index: 643

Text #14

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1488431 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1426428 (The Pile)

Max Activating Token Index: 569

Text #16

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1325722 (The Pile)

Max Activating Token Index: 245

Text #17

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2378. Min Act: -0.0000

Data Index: 1772470 (The Pile)

Max Activating Token Index: 193

Text #18

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2454. Min Act: -0.0000

Data Index: 1177948 (The Pile)

Max Activating Token Index: 262

Text #19

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2309. Min Act: -0.0000

Data Index: 884851 (The Pile)

Max Activating Token Index: 38