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

Dataset: The Pile

Neuron 2514 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5682. Min Act: -0.0000

Data Index: 1765708 (The Pile)

Max Activating Token Index: 853

Text #1

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.3821. Min Act: -0.0000

Data Index: 1520372 (The Pile)

Max Activating Token Index: 882

Text #2

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5451. Min Act: -0.0000

Data Index: 584213 (The Pile)

Max Activating Token Index: 454

Text #3

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.4520. Min Act: -0.0000

Data Index: 1567481 (The Pile)

Max Activating Token Index: 443

Text #4

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5027. Min Act: -0.0000

Data Index: 1362947 (The Pile)

Max Activating Token Index: 789

Text #5

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.4277. Min Act: -0.0000

Data Index: 1923288 (The Pile)

Max Activating Token Index: 191

Text #6

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2401. Min Act: -0.0000

Data Index: 1748592 (The Pile)

Max Activating Token Index: 269

Text #7

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.3053. Min Act: -0.0000

Data Index: 948247 (The Pile)

Max Activating Token Index: 68

Text #8

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2808. Min Act: -0.0000

Data Index: 1789986 (The Pile)

Max Activating Token Index: 967

Text #9

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2562. Min Act: -0.0000

Data Index: 1340298 (The Pile)

Max Activating Token Index: 175

Text #10

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.3246. Min Act: -0.0000

Data Index: 1183765 (The Pile)

Max Activating Token Index: 668

Text #11

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.3109. Min Act: -0.0000

Data Index: 1234093 (The Pile)

Max Activating Token Index: 256

Text #12

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2280. Min Act: -0.0000

Data Index: 423383 (The Pile)

Max Activating Token Index: 293

Text #13

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2298. Min Act: -0.0000

Data Index: 1181305 (The Pile)

Max Activating Token Index: 122

Text #14

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2880. Min Act: -0.0000

Data Index: 696538 (The Pile)

Max Activating Token Index: 726

Text #15

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.1537. Min Act: -0.0000

Data Index: 196893 (The Pile)

Max Activating Token Index: 32

Text #16

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2267. Min Act: -0.0000

Data Index: 798968 (The Pile)

Max Activating Token Index: 761

Text #17

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.0883. Min Act: -0.0000

Data Index: 1932805 (The Pile)

Max Activating Token Index: 676

Text #18

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2182. Min Act: -0.0000

Data Index: 526534 (The Pile)

Max Activating Token Index: 941

Text #19

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.1383. Min Act: -0.0000

Data Index: 1400001 (The Pile)

Max Activating Token Index: 179