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

Dataset: The Pile

Neuron 2941 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: 0.3157. Min Range: -0.3157

Max Act: 0.3157. Min Act: -0.0000

Data Index: 1964276 (The Pile)

Max Activating Token Index: 909

Text #1

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2776. Min Act: -0.0000

Data Index: 1723605 (The Pile)

Max Activating Token Index: 518

Text #2

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2545. Min Act: -0.0000

Data Index: 1707647 (The Pile)

Max Activating Token Index: 603

Text #3

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2676. Min Act: -0.0000

Data Index: 1748997 (The Pile)

Max Activating Token Index: 779

Text #4

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1781089 (The Pile)

Max Activating Token Index: 269

Text #5

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2517. Min Act: -0.0000

Data Index: 1846963 (The Pile)

Max Activating Token Index: 138

Text #6

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2399. Min Act: -0.0000

Data Index: 675027 (The Pile)

Max Activating Token Index: 613

Text #7

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2401. Min Act: -0.0000

Data Index: 1054703 (The Pile)

Max Activating Token Index: 528

Text #8

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2366. Min Act: -0.0000

Data Index: 1710984 (The Pile)

Max Activating Token Index: 91

Text #9

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2350. Min Act: -0.0000

Data Index: 754064 (The Pile)

Max Activating Token Index: 334

Text #10

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2416. Min Act: -0.0000

Data Index: 986239 (The Pile)

Max Activating Token Index: 589

Text #11

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2421. Min Act: -0.0000

Data Index: 455004 (The Pile)

Max Activating Token Index: 682

Text #12

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2418. Min Act: -0.0000

Data Index: 834724 (The Pile)

Max Activating Token Index: 377

Text #13

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2479. Min Act: -0.0000

Data Index: 708814 (The Pile)

Max Activating Token Index: 31

Text #14

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2380. Min Act: -0.0000

Data Index: 1255603 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2445. Min Act: -0.0000

Data Index: 1613174 (The Pile)

Max Activating Token Index: 916

Text #16

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1880347 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1694263 (The Pile)

Max Activating Token Index: 231

Text #18

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2340. Min Act: -0.0000

Data Index: 861814 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1268275 (The Pile)

Max Activating Token Index: 361