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

Dataset: The Pile

Neuron 4937 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.4951. Min Act: -0.0000

Data Index: 384826 (The Pile)

Max Activating Token Index: 379

Text #1

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.4586. Min Act: -0.0000

Data Index: 753268 (The Pile)

Max Activating Token Index: 406

Text #2

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.4386. Min Act: -0.0000

Data Index: 1727422 (The Pile)

Max Activating Token Index: 270

Text #3

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.4493. Min Act: -0.0000

Data Index: 990069 (The Pile)

Max Activating Token Index: 606

Text #4

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.4499. Min Act: -0.0000

Data Index: 1762532 (The Pile)

Max Activating Token Index: 166

Text #5

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3625. Min Act: -0.0000

Data Index: 1003774 (The Pile)

Max Activating Token Index: 273

Text #6

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3793. Min Act: -0.0000

Data Index: 1031222 (The Pile)

Max Activating Token Index: 628

Text #7

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.2515. Min Act: -0.0000

Data Index: 1591831 (The Pile)

Max Activating Token Index: 303

Text #8

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.2831. Min Act: -0.0000

Data Index: 1922113 (The Pile)

Max Activating Token Index: 461

Text #9

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.3474. Min Act: -0.0000

Data Index: 730142 (The Pile)

Max Activating Token Index: 717

Text #10

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.2827. Min Act: -0.0000

Data Index: 1467771 (The Pile)

Max Activating Token Index: 979

Text #11

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.2220. Min Act: -0.0000

Data Index: 1777846 (The Pile)

Max Activating Token Index: 434

Text #12

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.2340. Min Act: -0.0000

Data Index: 1921461 (The Pile)

Max Activating Token Index: 323

Text #13

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.2326. Min Act: -0.0000

Data Index: 1505580 (The Pile)

Max Activating Token Index: 635

Text #14

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.1340. Min Act: -0.0000

Data Index: 906768 (The Pile)

Max Activating Token Index: 89

Text #15

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.1850. Min Act: -0.0000

Data Index: 793168 (The Pile)

Max Activating Token Index: 925

Text #16

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.2276. Min Act: -0.0000

Data Index: 353989 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 1.4951. Min Range: -1.4951

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1320939 (The Pile)

Max Activating Token Index: 863

Text #18

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.1103. Min Act: -0.0000

Data Index: 1535932 (The Pile)

Max Activating Token Index: 743

Text #19

Max Range: 1.4951. Min Range: -1.4951

Max Act: 1.1257. Min Act: -0.0000

Data Index: 1682985 (The Pile)

Max Activating Token Index: 434