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

Dataset: The Pile

Neuron 4622 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2367. Min Act: -0.0000

Data Index: 442845 (The Pile)

Max Activating Token Index: 750

Text #1

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2427. Min Act: -0.0000

Data Index: 1933355 (The Pile)

Max Activating Token Index: 510

Text #2

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2359. Min Act: -0.0000

Data Index: 1023468 (The Pile)

Max Activating Token Index: 587

Text #3

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2531. Min Act: -0.0000

Data Index: 246737 (The Pile)

Max Activating Token Index: 1014

Text #4

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2442. Min Act: -0.0000

Data Index: 884777 (The Pile)

Max Activating Token Index: 352

Text #5

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2148. Min Act: -0.0000

Data Index: 591362 (The Pile)

Max Activating Token Index: 972

Text #6

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1524009 (The Pile)

Max Activating Token Index: 939

Text #7

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2129. Min Act: -0.0000

Data Index: 1254789 (The Pile)

Max Activating Token Index: 968

Text #8

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1894. Min Act: -0.0000

Data Index: 290396 (The Pile)

Max Activating Token Index: 711

Text #9

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2286. Min Act: -0.0000

Data Index: 1390061 (The Pile)

Max Activating Token Index: 981

Text #10

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2209. Min Act: -0.0000

Data Index: 759764 (The Pile)

Max Activating Token Index: 489

Text #11

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2280. Min Act: -0.0000

Data Index: 125367 (The Pile)

Max Activating Token Index: 694

Text #12

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1703. Min Act: -0.0000

Data Index: 1210266 (The Pile)

Max Activating Token Index: 787

Text #13

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2235. Min Act: -0.0000

Data Index: 958591 (The Pile)

Max Activating Token Index: 980

Text #14

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1732. Min Act: -0.0000

Data Index: 1221100 (The Pile)

Max Activating Token Index: 827

Text #15

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1932. Min Act: -0.0000

Data Index: 1220832 (The Pile)

Max Activating Token Index: 819

Text #16

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2214. Min Act: -0.0000

Data Index: 36649 (The Pile)

Max Activating Token Index: 871

Text #17

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1922. Min Act: -0.0000

Data Index: 1002583 (The Pile)

Max Activating Token Index: 985

Text #18

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2102. Min Act: -0.0000

Data Index: 913748 (The Pile)

Max Activating Token Index: 871

Text #19

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2055. Min Act: -0.0000

Data Index: 304527 (The Pile)

Max Activating Token Index: 963