Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2789 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.3063. Min Act: -0.0000

Data Index: 1205618 (The Pile)

Max Activating Token Index: 751

Text #1

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2668. Min Act: -0.0000

Data Index: 692640 (The Pile)

Max Activating Token Index: 655

Text #2

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2731. Min Act: -0.0000

Data Index: 512530 (The Pile)

Max Activating Token Index: 123

Text #3

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2524. Min Act: -0.0000

Data Index: 1693872 (The Pile)

Max Activating Token Index: 629

Text #4

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2424. Min Act: -0.0000

Data Index: 1681101 (The Pile)

Max Activating Token Index: 932

Text #5

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2416. Min Act: -0.0000

Data Index: 372328 (The Pile)

Max Activating Token Index: 321

Text #6

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2252. Min Act: -0.0000

Data Index: 540886 (The Pile)

Max Activating Token Index: 523

Text #7

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2309. Min Act: -0.0000

Data Index: 408827 (The Pile)

Max Activating Token Index: 40

Text #8

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2319. Min Act: -0.0000

Data Index: 1779224 (The Pile)

Max Activating Token Index: 776

Text #9

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2442. Min Act: -0.0000

Data Index: 1575119 (The Pile)

Max Activating Token Index: 948

Text #10

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2139. Min Act: -0.0000

Data Index: 233115 (The Pile)

Max Activating Token Index: 439

Text #11

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2350. Min Act: -0.0000

Data Index: 501890 (The Pile)

Max Activating Token Index: 376

Text #12

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1239663 (The Pile)

Max Activating Token Index: 452

Text #13

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2209. Min Act: -0.0000

Data Index: 92092 (The Pile)

Max Activating Token Index: 640

Text #14

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2036. Min Act: -0.0000

Data Index: 1385271 (The Pile)

Max Activating Token Index: 158

Text #15

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1146249 (The Pile)

Max Activating Token Index: 538

Text #16

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.1878. Min Act: -0.0000

Data Index: 1577331 (The Pile)

Max Activating Token Index: 600

Text #17

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1336917 (The Pile)

Max Activating Token Index: 954

Text #18

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1171261 (The Pile)

Max Activating Token Index: 428

Text #19

Max Range: 0.3063. Min Range: -0.3063

Max Act: 0.2144. Min Act: -0.0000

Data Index: 1050429 (The Pile)

Max Activating Token Index: 413