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

Dataset: The Pile

Neuron 4644 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: 0.6867. Min Range: -0.6867

Max Act: 0.6867. Min Act: -0.0000

Data Index: 214238 (The Pile)

Max Activating Token Index: 649

Text #1

Max Range: 0.6867. Min Range: -0.6867

Max Act: 0.5627. Min Act: -0.0000

Data Index: 1591392 (The Pile)

Max Activating Token Index: 779

Text #2

Max Range: 0.6867. Min Range: -0.6867

Max Act: 0.5896. Min Act: -0.0000

Data Index: 742377 (The Pile)

Max Activating Token Index: 47

Text #3

Max Range: 0.6867. Min Range: -0.6867

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1493429 (The Pile)

Max Activating Token Index: 373

Text #4

Max Range: 0.6867. Min Range: -0.6867

Max Act: 0.5423. Min Act: -0.0000

Data Index: 1778672 (The Pile)

Max Activating Token Index: 48

Text #5

Max Range: 0.6867. Min Range: -0.6867

Max Act: 0.5302. Min Act: -0.0000

Data Index: 401610 (The Pile)

Max Activating Token Index: 294

Text #6

Max Range: 0.6867. Min Range: -0.6867

Max Act: 0.4880. Min Act: -0.0000

Data Index: 12317 (The Pile)

Max Activating Token Index: 431

Text #7

Max Range: 0.6867. Min Range: -0.6867

Max Act: 0.5174. Min Act: -0.0000

Data Index: 948909 (The Pile)

Max Activating Token Index: 242

Text #8

Max Range: 0.6867. Min Range: -0.6867

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1189816 (The Pile)

Max Activating Token Index: 974

Text #9

Max Range: 0.6867. Min Range: -0.6867

Max Act: 0.5136. Min Act: -0.0000

Data Index: 1862853 (The Pile)

Max Activating Token Index: 864

Text #10

Max Range: 0.6867. Min Range: -0.6867

Max Act: 0.4835. Min Act: -0.0000

Data Index: 756634 (The Pile)

Max Activating Token Index: 572

Text #11

Max Range: 0.6867. Min Range: -0.6867

Max Act: 0.4618. Min Act: -0.0000

Data Index: 1448846 (The Pile)

Max Activating Token Index: 903

Text #12

Max Range: 0.6867. Min Range: -0.6867

Max Act: 0.5089. Min Act: -0.0000

Data Index: 239656 (The Pile)

Max Activating Token Index: 420

Text #13

Max Range: 0.6867. Min Range: -0.6867

Max Act: 0.5018. Min Act: -0.0000

Data Index: 350108 (The Pile)

Max Activating Token Index: 731

Text #14

Max Range: 0.6867. Min Range: -0.6867

Max Act: 0.5187. Min Act: -0.0000

Data Index: 1537643 (The Pile)

Max Activating Token Index: 746

Text #15

Max Range: 0.6867. Min Range: -0.6867

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1344761 (The Pile)

Max Activating Token Index: 358

Text #16

Max Range: 0.6867. Min Range: -0.6867

Max Act: 0.4930. Min Act: -0.0000

Data Index: 575163 (The Pile)

Max Activating Token Index: 119

Text #17

Max Range: 0.6867. Min Range: -0.6867

Max Act: 0.4829. Min Act: -0.0000

Data Index: 1592823 (The Pile)

Max Activating Token Index: 488

Text #18

Max Range: 0.6867. Min Range: -0.6867

Max Act: 0.3982. Min Act: -0.0000

Data Index: 1236841 (The Pile)

Max Activating Token Index: 663

Text #19

Max Range: 0.6867. Min Range: -0.6867

Max Act: 0.4489. Min Act: -0.0000

Data Index: 592907 (The Pile)

Max Activating Token Index: 987