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

Dataset: The Pile

Neuron 2255 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: 0.3883. Min Range: -0.3883

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1124246 (The Pile)

Max Activating Token Index: 844

Text #1

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3742. Min Act: -0.0000

Data Index: 1561783 (The Pile)

Max Activating Token Index: 140

Text #2

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3231. Min Act: -0.0000

Data Index: 1959236 (The Pile)

Max Activating Token Index: 460

Text #3

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1550860 (The Pile)

Max Activating Token Index: 405

Text #4

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3724. Min Act: -0.0000

Data Index: 889226 (The Pile)

Max Activating Token Index: 596

Text #5

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3315. Min Act: -0.0000

Data Index: 533484 (The Pile)

Max Activating Token Index: 823

Text #6

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3253. Min Act: -0.0000

Data Index: 1828394 (The Pile)

Max Activating Token Index: 565

Text #7

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3421. Min Act: -0.0000

Data Index: 662973 (The Pile)

Max Activating Token Index: 723

Text #8

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3276. Min Act: -0.0000

Data Index: 461533 (The Pile)

Max Activating Token Index: 21

Text #9

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3261. Min Act: -0.0000

Data Index: 528479 (The Pile)

Max Activating Token Index: 313

Text #10

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1572191 (The Pile)

Max Activating Token Index: 759

Text #11

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3195. Min Act: -0.0000

Data Index: 1573086 (The Pile)

Max Activating Token Index: 515

Text #12

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3014. Min Act: 0.0001

Data Index: 774009 (The Pile)

Max Activating Token Index: 42

Text #13

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.2512. Min Act: -0.0000

Data Index: 482026 (The Pile)

Max Activating Token Index: 630

Text #14

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3188. Min Act: -0.0000

Data Index: 67522 (The Pile)

Max Activating Token Index: 464

Text #15

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3017. Min Act: -0.0000

Data Index: 628569 (The Pile)

Max Activating Token Index: 513

Text #16

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.2983. Min Act: -0.0000

Data Index: 1446748 (The Pile)

Max Activating Token Index: 803

Text #17

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.3222. Min Act: -0.0000

Data Index: 1274861 (The Pile)

Max Activating Token Index: 176

Text #18

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.2797. Min Act: -0.0000

Data Index: 708500 (The Pile)

Max Activating Token Index: 269

Text #19

Max Range: 0.3883. Min Range: -0.3883

Max Act: 0.2986. Min Act: -0.0000

Data Index: 432888 (The Pile)

Max Activating Token Index: 368