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

Dataset: The Pile

Neuron 4310 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: 0.5937. Min Range: -0.5937

Max Act: 0.5937. Min Act: -0.0000

Data Index: 1883772 (The Pile)

Max Activating Token Index: 490

Text #1

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1675277 (The Pile)

Max Activating Token Index: 362

Text #2

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5648. Min Act: -0.0000

Data Index: 1717329 (The Pile)

Max Activating Token Index: 425

Text #3

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5141. Min Act: -0.0000

Data Index: 425614 (The Pile)

Max Activating Token Index: 582

Text #4

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5353. Min Act: -0.0000

Data Index: 73023 (The Pile)

Max Activating Token Index: 477

Text #5

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1009253 (The Pile)

Max Activating Token Index: 368

Text #6

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1475715 (The Pile)

Max Activating Token Index: 282

Text #7

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5466. Min Act: -0.0000

Data Index: 793678 (The Pile)

Max Activating Token Index: 405

Text #8

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1924549 (The Pile)

Max Activating Token Index: 385

Text #9

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1185493 (The Pile)

Max Activating Token Index: 392

Text #10

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5094. Min Act: -0.0000

Data Index: 919811 (The Pile)

Max Activating Token Index: 459

Text #11

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5279. Min Act: -0.0000

Data Index: 566858 (The Pile)

Max Activating Token Index: 459

Text #12

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1730535 (The Pile)

Max Activating Token Index: 435

Text #13

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5075. Min Act: -0.0000

Data Index: 246537 (The Pile)

Max Activating Token Index: 385

Text #14

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4899. Min Act: -0.0000

Data Index: 768509 (The Pile)

Max Activating Token Index: 655

Text #15

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.5219. Min Act: -0.0000

Data Index: 608907 (The Pile)

Max Activating Token Index: 370

Text #16

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1103031 (The Pile)

Max Activating Token Index: 322

Text #17

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4985. Min Act: -0.0000

Data Index: 507999 (The Pile)

Max Activating Token Index: 400

Text #18

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4488. Min Act: -0.0000

Data Index: 549532 (The Pile)

Max Activating Token Index: 787

Text #19

Max Range: 0.5937. Min Range: -0.5937

Max Act: 0.4935. Min Act: -0.0000

Data Index: 1451531 (The Pile)

Max Activating Token Index: 328