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

Dataset: The Pile

Neuron 1955 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: 1.3581. Min Range: -1.3581

Max Act: 1.3581. Min Act: -0.0000

Data Index: 1490859 (The Pile)

Max Activating Token Index: 172

Text #1

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.3170. Min Act: -0.0000

Data Index: 615353 (The Pile)

Max Activating Token Index: 349

Text #2

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.1892. Min Act: -0.0000

Data Index: 34349 (The Pile)

Max Activating Token Index: 835

Text #3

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.0958. Min Act: -0.0000

Data Index: 260805 (The Pile)

Max Activating Token Index: 222

Text #4

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.1316. Min Act: -0.0000

Data Index: 229394 (The Pile)

Max Activating Token Index: 590

Text #5

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.1312. Min Act: -0.0000

Data Index: 347768 (The Pile)

Max Activating Token Index: 322

Text #6

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.0577. Min Act: -0.0000

Data Index: 1800198 (The Pile)

Max Activating Token Index: 322

Text #7

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.1967. Min Act: -0.0000

Data Index: 340192 (The Pile)

Max Activating Token Index: 320

Text #8

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.0782. Min Act: -0.0000

Data Index: 335274 (The Pile)

Max Activating Token Index: 639

Text #9

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.0811. Min Act: -0.0000

Data Index: 312389 (The Pile)

Max Activating Token Index: 358

Text #10

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.1423. Min Act: -0.0000

Data Index: 1166783 (The Pile)

Max Activating Token Index: 712

Text #11

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.0869. Min Act: -0.0000

Data Index: 324600 (The Pile)

Max Activating Token Index: 51

Text #12

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1913960 (The Pile)

Max Activating Token Index: 243

Text #13

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.9935. Min Act: -0.0000

Data Index: 384287 (The Pile)

Max Activating Token Index: 384

Text #14

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.1124. Min Act: -0.0000

Data Index: 744577 (The Pile)

Max Activating Token Index: 821

Text #15

Max Range: 1.3581. Min Range: -1.3581

Max Act: 1.0303. Min Act: -0.0000

Data Index: 886362 (The Pile)

Max Activating Token Index: 758

Text #16

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1751659 (The Pile)

Max Activating Token Index: 117

Text #17

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.9583. Min Act: -0.0000

Data Index: 1416035 (The Pile)

Max Activating Token Index: 871

Text #18

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.8743. Min Act: -0.0000

Data Index: 1895954 (The Pile)

Max Activating Token Index: 69

Text #19

Max Range: 1.3581. Min Range: -1.3581

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1490195 (The Pile)

Max Activating Token Index: 311