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

Dataset: The Pile

Neuron 3070 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: 1.4475. Min Range: -1.4475

Max Act: 1.4475. Min Act: -0.0000

Data Index: 1190021 (The Pile)

Max Activating Token Index: 740

Text #1

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.4319. Min Act: -0.0000

Data Index: 1171582 (The Pile)

Max Activating Token Index: 631

Text #2

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.3632. Min Act: -0.0000

Data Index: 1401235 (The Pile)

Max Activating Token Index: 929

Text #3

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.4105. Min Act: -0.0000

Data Index: 380014 (The Pile)

Max Activating Token Index: 854

Text #4

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.2587. Min Act: -0.0000

Data Index: 733551 (The Pile)

Max Activating Token Index: 949

Text #5

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.2038. Min Act: -0.0000

Data Index: 1766246 (The Pile)

Max Activating Token Index: 739

Text #6

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.1491. Min Act: -0.0000

Data Index: 561357 (The Pile)

Max Activating Token Index: 93

Text #7

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.0343. Min Act: -0.0000

Data Index: 1819506 (The Pile)

Max Activating Token Index: 99

Text #8

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.2073. Min Act: -0.0000

Data Index: 1832791 (The Pile)

Max Activating Token Index: 442

Text #9

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.1195. Min Act: -0.0000

Data Index: 161296 (The Pile)

Max Activating Token Index: 308

Text #10

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.1084. Min Act: -0.0000

Data Index: 1596540 (The Pile)

Max Activating Token Index: 996

Text #11

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.0331. Min Act: -0.0000

Data Index: 1750036 (The Pile)

Max Activating Token Index: 951

Text #12

Max Range: 1.4475. Min Range: -1.4475

Max Act: 0.9690. Min Act: -0.0000

Data Index: 532941 (The Pile)

Max Activating Token Index: 963

Text #13

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.1305. Min Act: -0.0000

Data Index: 1610535 (The Pile)

Max Activating Token Index: 56

Text #14

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.0794. Min Act: -0.0000

Data Index: 1054265 (The Pile)

Max Activating Token Index: 465

Text #15

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.0578. Min Act: -0.0000

Data Index: 1045365 (The Pile)

Max Activating Token Index: 326

Text #16

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.0821. Min Act: -0.0000

Data Index: 1351851 (The Pile)

Max Activating Token Index: 388

Text #17

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.0411. Min Act: -0.0000

Data Index: 607134 (The Pile)

Max Activating Token Index: 523

Text #18

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.0765. Min Act: -0.0000

Data Index: 1635887 (The Pile)

Max Activating Token Index: 350

Text #19

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.0292. Min Act: -0.0000

Data Index: 1975707 (The Pile)

Max Activating Token Index: 756