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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1073 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0872. Min Act: -0.0003

Data Index: 638495 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0835. Min Act: -0.0003

Data Index: 1046004 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1091926 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0594. Min Act: -0.0003

Data Index: 356553 (C4 (Web Text))

Max Activating Token Index: 445

Text #4

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0545. Min Act: -0.0003

Data Index: 348076 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0574. Min Act: -0.0003

Data Index: 308406 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1319893 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0519. Min Act: -0.0003

Data Index: 1094634 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0524. Min Act: -0.0003

Data Index: 538056 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0516. Min Act: -0.0003

Data Index: 790789 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0523. Min Act: -0.0003

Data Index: 402316 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0513. Min Act: -0.0003

Data Index: 582126 (C4 (Web Text))

Max Activating Token Index: 165

Text #12

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0507. Min Act: -0.0003

Data Index: 1269482 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0492. Min Act: -0.0003

Data Index: 247059 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0472. Min Act: -0.0003

Data Index: 501777 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0476. Min Act: -0.0003

Data Index: 238487 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0464. Min Act: -0.0003

Data Index: 325591 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1245040 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0480. Min Act: -0.0003

Data Index: 856237 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 0.0872. Min Range: -0.0872

Max Act: 0.0451. Min Act: -0.0003

Data Index: 398849 (C4 (Web Text))

Max Activating Token Index: 199