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

Dataset: The Pile

Neuron 66 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: 1.4522. Min Range: -1.4522

Max Act: 1.4522. Min Act: -0.0000

Data Index: 422178 (The Pile)

Max Activating Token Index: 529

Text #1

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.3808. Min Act: -0.0000

Data Index: 1524127 (The Pile)

Max Activating Token Index: 634

Text #2

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.4231. Min Act: -0.0000

Data Index: 914926 (The Pile)

Max Activating Token Index: 621

Text #3

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2736. Min Act: -0.0000

Data Index: 1801430 (The Pile)

Max Activating Token Index: 538

Text #4

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.3567. Min Act: -0.0000

Data Index: 1929980 (The Pile)

Max Activating Token Index: 762

Text #5

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.3622. Min Act: -0.0000

Data Index: 1615307 (The Pile)

Max Activating Token Index: 597

Text #6

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2632. Min Act: -0.0000

Data Index: 869526 (The Pile)

Max Activating Token Index: 568

Text #7

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2665. Min Act: -0.0000

Data Index: 306430 (The Pile)

Max Activating Token Index: 469

Text #8

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2581. Min Act: -0.0000

Data Index: 1094398 (The Pile)

Max Activating Token Index: 263

Text #9

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2930. Min Act: -0.0000

Data Index: 349042 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.3667. Min Act: -0.0000

Data Index: 1954183 (The Pile)

Max Activating Token Index: 721

Text #11

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.3127. Min Act: -0.0000

Data Index: 510925 (The Pile)

Max Activating Token Index: 492

Text #12

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.3132. Min Act: -0.0000

Data Index: 677283 (The Pile)

Max Activating Token Index: 822

Text #13

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.3755. Min Act: -0.0000

Data Index: 281731 (The Pile)

Max Activating Token Index: 445

Text #14

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.1988. Min Act: -0.0000

Data Index: 1501982 (The Pile)

Max Activating Token Index: 615

Text #15

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.1665. Min Act: -0.0000

Data Index: 1091161 (The Pile)

Max Activating Token Index: 856

Text #16

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2591. Min Act: -0.0000

Data Index: 416939 (The Pile)

Max Activating Token Index: 648

Text #17

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2056. Min Act: -0.0000

Data Index: 362266 (The Pile)

Max Activating Token Index: 227

Text #18

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2029. Min Act: -0.0000

Data Index: 86132 (The Pile)

Max Activating Token Index: 860

Text #19

Max Range: 1.4522. Min Range: -1.4522

Max Act: 1.2361. Min Act: -0.0000

Data Index: 1248257 (The Pile)

Max Activating Token Index: 242