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

Dataset: The Pile

Neuron 912 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: 0.6761. Min Range: -0.6761

Max Act: 0.6761. Min Act: -0.0000

Data Index: 312821 (The Pile)

Max Activating Token Index: 522

Text #1

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.6270. Min Act: -0.0000

Data Index: 793191 (The Pile)

Max Activating Token Index: 599

Text #2

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1726130 (The Pile)

Max Activating Token Index: 389

Text #3

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.6119. Min Act: -0.0000

Data Index: 1688530 (The Pile)

Max Activating Token Index: 688

Text #4

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1872157 (The Pile)

Max Activating Token Index: 733

Text #5

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1743579 (The Pile)

Max Activating Token Index: 986

Text #6

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1005273 (The Pile)

Max Activating Token Index: 74

Text #7

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5616. Min Act: -0.0000

Data Index: 363177 (The Pile)

Max Activating Token Index: 388

Text #8

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1089389 (The Pile)

Max Activating Token Index: 593

Text #9

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5218. Min Act: -0.0000

Data Index: 937661 (The Pile)

Max Activating Token Index: 746

Text #10

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1154287 (The Pile)

Max Activating Token Index: 46

Text #11

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1565283 (The Pile)

Max Activating Token Index: 206

Text #12

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1893718 (The Pile)

Max Activating Token Index: 758

Text #13

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5087. Min Act: -0.0000

Data Index: 507381 (The Pile)

Max Activating Token Index: 512

Text #14

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1723577 (The Pile)

Max Activating Token Index: 133

Text #15

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.4759. Min Act: -0.0000

Data Index: 571432 (The Pile)

Max Activating Token Index: 877

Text #16

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5185. Min Act: -0.0000

Data Index: 249409 (The Pile)

Max Activating Token Index: 959

Text #17

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5121. Min Act: -0.0000

Data Index: 1106633 (The Pile)

Max Activating Token Index: 659

Text #18

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5240. Min Act: -0.0000

Data Index: 1187133 (The Pile)

Max Activating Token Index: 524

Text #19

Max Range: 0.6761. Min Range: -0.6761

Max Act: 0.5003. Min Act: -0.0000

Data Index: 1049555 (The Pile)

Max Activating Token Index: 943