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

Dataset: The Pile

Neuron 4242 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.3668. Min Act: -0.0000

Data Index: 965309 (The Pile)

Max Activating Token Index: 564

Text #1

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.0788. Min Act: -0.0000

Data Index: 796619 (The Pile)

Max Activating Token Index: 587

Text #2

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.0903. Min Act: -0.0000

Data Index: 1340727 (The Pile)

Max Activating Token Index: 307

Text #3

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.1526. Min Act: -0.0000

Data Index: 78566 (The Pile)

Max Activating Token Index: 322

Text #4

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.0190. Min Act: -0.0000

Data Index: 1570822 (The Pile)

Max Activating Token Index: 413

Text #5

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.1046. Min Act: -0.0000

Data Index: 451075 (The Pile)

Max Activating Token Index: 541

Text #6

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.0362. Min Act: -0.0000

Data Index: 1072169 (The Pile)

Max Activating Token Index: 1017

Text #7

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.0626. Min Act: -0.0000

Data Index: 1816473 (The Pile)

Max Activating Token Index: 56

Text #8

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1633571 (The Pile)

Max Activating Token Index: 923

Text #9

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.0283. Min Act: -0.0000

Data Index: 1325516 (The Pile)

Max Activating Token Index: 66

Text #10

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.8307. Min Act: -0.0000

Data Index: 1691726 (The Pile)

Max Activating Token Index: 180

Text #11

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.9789. Min Act: -0.0000

Data Index: 1975678 (The Pile)

Max Activating Token Index: 334

Text #12

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.0691. Min Act: -0.0000

Data Index: 631436 (The Pile)

Max Activating Token Index: 542

Text #13

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.2516. Min Act: -0.0000

Data Index: 1512579 (The Pile)

Max Activating Token Index: 90

Text #14

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.0915. Min Act: -0.0000

Data Index: 1426634 (The Pile)

Max Activating Token Index: 341

Text #15

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.9280. Min Act: -0.0000

Data Index: 1339739 (The Pile)

Max Activating Token Index: 396

Text #16

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.9997. Min Act: -0.0000

Data Index: 692309 (The Pile)

Max Activating Token Index: 245

Text #17

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.9478. Min Act: -0.0000

Data Index: 1178600 (The Pile)

Max Activating Token Index: 613

Text #18

Max Range: 1.3668. Min Range: -1.3668

Max Act: 1.1594. Min Act: -0.0000

Data Index: 1505088 (The Pile)

Max Activating Token Index: 66

Text #19

Max Range: 1.3668. Min Range: -1.3668

Max Act: 0.7796. Min Act: -0.0000

Data Index: 201249 (The Pile)

Max Activating Token Index: 853