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

Dataset: The Pile

Neuron 4127 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: 1.4661. Min Range: -1.4661

Max Act: 1.2128. Min Act: -0.0000

Data Index: 1521626 (The Pile)

Max Activating Token Index: 634

Text #1

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.4661. Min Act: -0.0000

Data Index: 829534 (The Pile)

Max Activating Token Index: 754

Text #2

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.3149. Min Act: -0.0000

Data Index: 1662279 (The Pile)

Max Activating Token Index: 268

Text #3

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.2525. Min Act: -0.0000

Data Index: 472807 (The Pile)

Max Activating Token Index: 835

Text #4

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.2886. Min Act: -0.0000

Data Index: 1026972 (The Pile)

Max Activating Token Index: 564

Text #5

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.2410. Min Act: -0.0000

Data Index: 1562650 (The Pile)

Max Activating Token Index: 772

Text #6

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.2272. Min Act: -0.0000

Data Index: 830400 (The Pile)

Max Activating Token Index: 443

Text #7

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.2648. Min Act: -0.0000

Data Index: 1203071 (The Pile)

Max Activating Token Index: 407

Text #8

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.1662. Min Act: -0.0000

Data Index: 1009303 (The Pile)

Max Activating Token Index: 78

Text #9

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.2713. Min Act: -0.0000

Data Index: 1711964 (The Pile)

Max Activating Token Index: 538

Text #10

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.1980. Min Act: -0.0000

Data Index: 760231 (The Pile)

Max Activating Token Index: 393

Text #11

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.1374. Min Act: -0.0000

Data Index: 224633 (The Pile)

Max Activating Token Index: 965

Text #12

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.2212. Min Act: -0.0000

Data Index: 1134810 (The Pile)

Max Activating Token Index: 467

Text #13

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.1231. Min Act: -0.0000

Data Index: 1808275 (The Pile)

Max Activating Token Index: 922

Text #14

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.2767. Min Act: -0.0000

Data Index: 529942 (The Pile)

Max Activating Token Index: 242

Text #15

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.2875. Min Act: -0.0000

Data Index: 70605 (The Pile)

Max Activating Token Index: 468

Text #16

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.1367. Min Act: -0.0000

Data Index: 266705 (The Pile)

Max Activating Token Index: 277

Text #17

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.2471. Min Act: -0.0000

Data Index: 1698862 (The Pile)

Max Activating Token Index: 348

Text #18

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.2226. Min Act: -0.0000

Data Index: 1292148 (The Pile)

Max Activating Token Index: 832

Text #19

Max Range: 1.4661. Min Range: -1.4661

Max Act: 1.0750. Min Act: -0.0000

Data Index: 1922448 (The Pile)

Max Activating Token Index: 811