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

Dataset: The Pile

Neuron 1254 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.5745. Min Act: -0.0000

Data Index: 693533 (The Pile)

Max Activating Token Index: 633

Text #1

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.5361. Min Act: -0.0000

Data Index: 394280 (The Pile)

Max Activating Token Index: 379

Text #2

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4932. Min Act: -0.0000

Data Index: 284152 (The Pile)

Max Activating Token Index: 1002

Text #3

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4789. Min Act: -0.0000

Data Index: 1589266 (The Pile)

Max Activating Token Index: 754

Text #4

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4826. Min Act: -0.0000

Data Index: 907536 (The Pile)

Max Activating Token Index: 427

Text #5

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4313. Min Act: -0.0000

Data Index: 1490454 (The Pile)

Max Activating Token Index: 487

Text #6

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4970. Min Act: -0.0000

Data Index: 775625 (The Pile)

Max Activating Token Index: 853

Text #7

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4295. Min Act: -0.0000

Data Index: 1165967 (The Pile)

Max Activating Token Index: 653

Text #8

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.5005. Min Act: -0.0000

Data Index: 1289245 (The Pile)

Max Activating Token Index: 751

Text #9

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4562. Min Act: -0.0000

Data Index: 949542 (The Pile)

Max Activating Token Index: 429

Text #10

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4377. Min Act: -0.0000

Data Index: 1308131 (The Pile)

Max Activating Token Index: 540

Text #11

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4223. Min Act: -0.0000

Data Index: 821071 (The Pile)

Max Activating Token Index: 739

Text #12

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4397. Min Act: -0.0000

Data Index: 160034 (The Pile)

Max Activating Token Index: 981

Text #13

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4295. Min Act: -0.0000

Data Index: 1873098 (The Pile)

Max Activating Token Index: 364

Text #14

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4255. Min Act: -0.0000

Data Index: 1743315 (The Pile)

Max Activating Token Index: 865

Text #15

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4248. Min Act: -0.0000

Data Index: 494970 (The Pile)

Max Activating Token Index: 756

Text #16

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4211. Min Act: -0.0000

Data Index: 639594 (The Pile)

Max Activating Token Index: 368

Text #17

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1573404 (The Pile)

Max Activating Token Index: 705

Text #18

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4431. Min Act: -0.0000

Data Index: 205899 (The Pile)

Max Activating Token Index: 717

Text #19

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1124634 (The Pile)

Max Activating Token Index: 492