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

Dataset: The Pile

Neuron 1902 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4335. Min Act: -0.0000

Data Index: 993351 (The Pile)

Max Activating Token Index: 533

Text #1

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4299. Min Act: -0.0000

Data Index: 1396914 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.4923. Min Act: -0.0000

Data Index: 737467 (The Pile)

Max Activating Token Index: 416

Text #3

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2499. Min Act: -0.0000

Data Index: 298798 (The Pile)

Max Activating Token Index: 231

Text #4

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2433. Min Act: -0.0000

Data Index: 1227733 (The Pile)

Max Activating Token Index: 881

Text #5

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.2338. Min Act: -0.0000

Data Index: 399913 (The Pile)

Max Activating Token Index: 880

Text #6

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.1932. Min Act: -0.0000

Data Index: 477737 (The Pile)

Max Activating Token Index: 582

Text #7

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.0590. Min Act: -0.0000

Data Index: 497702 (The Pile)

Max Activating Token Index: 580

Text #8

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.0891. Min Act: -0.0000

Data Index: 1466040 (The Pile)

Max Activating Token Index: 356

Text #9

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.0528. Min Act: -0.0000

Data Index: 346399 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.1410. Min Act: -0.0000

Data Index: 1919221 (The Pile)

Max Activating Token Index: 868

Text #11

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.0147. Min Act: -0.0000

Data Index: 1006225 (The Pile)

Max Activating Token Index: 958

Text #12

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.0422. Min Act: -0.0000

Data Index: 173196 (The Pile)

Max Activating Token Index: 805

Text #13

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.0334. Min Act: -0.0000

Data Index: 1548107 (The Pile)

Max Activating Token Index: 356

Text #14

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.0887. Min Act: -0.0000

Data Index: 1493487 (The Pile)

Max Activating Token Index: 833

Text #15

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.0190. Min Act: -0.0000

Data Index: 133198 (The Pile)

Max Activating Token Index: 719

Text #16

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.0154. Min Act: -0.0000

Data Index: 919502 (The Pile)

Max Activating Token Index: 112

Text #17

Max Range: 1.4923. Min Range: -1.4923

Max Act: 0.9886. Min Act: -0.0000

Data Index: 497567 (The Pile)

Max Activating Token Index: 730

Text #18

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.0086. Min Act: -0.0000

Data Index: 1526251 (The Pile)

Max Activating Token Index: 385

Text #19

Max Range: 1.4923. Min Range: -1.4923

Max Act: 1.0911. Min Act: -0.0000

Data Index: 293411 (The Pile)

Max Activating Token Index: 566