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

Dataset: The Pile

Neuron 3777 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.3172. Min Act: -0.0000

Data Index: 1328228 (The Pile)

Max Activating Token Index: 1001

Text #1

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.3782. Min Act: -0.0000

Data Index: 1979327 (The Pile)

Max Activating Token Index: 813

Text #2

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.4401. Min Act: -0.0000

Data Index: 372173 (The Pile)

Max Activating Token Index: 462

Text #3

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.2682. Min Act: -0.0000

Data Index: 584426 (The Pile)

Max Activating Token Index: 637

Text #4

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.3212. Min Act: -0.0000

Data Index: 806837 (The Pile)

Max Activating Token Index: 374

Text #5

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.3287. Min Act: -0.0000

Data Index: 34272 (The Pile)

Max Activating Token Index: 917

Text #6

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.2307. Min Act: -0.0000

Data Index: 359799 (The Pile)

Max Activating Token Index: 407

Text #7

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.4550. Min Act: -0.0000

Data Index: 1530785 (The Pile)

Max Activating Token Index: 835

Text #8

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.2180. Min Act: -0.0000

Data Index: 1254830 (The Pile)

Max Activating Token Index: 872

Text #9

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.2017. Min Act: -0.0000

Data Index: 1826831 (The Pile)

Max Activating Token Index: 308

Text #10

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.2935. Min Act: -0.0000

Data Index: 12304 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.2555. Min Act: -0.0000

Data Index: 733583 (The Pile)

Max Activating Token Index: 77

Text #12

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.2580. Min Act: -0.0000

Data Index: 792594 (The Pile)

Max Activating Token Index: 976

Text #13

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.1791. Min Act: -0.0000

Data Index: 136837 (The Pile)

Max Activating Token Index: 451

Text #14

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.0432. Min Act: -0.0000

Data Index: 1603533 (The Pile)

Max Activating Token Index: 612

Text #15

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.2028. Min Act: -0.0000

Data Index: 281562 (The Pile)

Max Activating Token Index: 292

Text #16

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.1319. Min Act: -0.0000

Data Index: 939758 (The Pile)

Max Activating Token Index: 261

Text #17

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.2672. Min Act: -0.0000

Data Index: 486647 (The Pile)

Max Activating Token Index: 883

Text #18

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.1938. Min Act: -0.0000

Data Index: 1247461 (The Pile)

Max Activating Token Index: 636

Text #19

Max Range: 1.4550. Min Range: -1.4550

Max Act: 1.0787. Min Act: -0.0000

Data Index: 755994 (The Pile)

Max Activating Token Index: 947