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

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

Neuron 2784 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.5681. Min Act: -0.0000

Data Index: 252040 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1091680 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4544. Min Act: -0.0000

Data Index: 614781 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4082. Min Act: -0.0000

Data Index: 221469 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4082. Min Act: -0.0000

Data Index: 110711 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4281. Min Act: -0.0000

Data Index: 12425 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4183. Min Act: -0.0000

Data Index: 368889 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.3789. Min Act: -0.0000

Data Index: 216579 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.4000. Min Act: -0.0000

Data Index: 112308 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1109289 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.3770. Min Act: -0.0000

Data Index: 732685 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.3582. Min Act: -0.0000

Data Index: 483810 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.3653. Min Act: -0.0000

Data Index: 1011121 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.3683. Min Act: -0.0000

Data Index: 308696 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.3773. Min Act: -0.0000

Data Index: 116064 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1036489 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.3440. Min Act: -0.0000

Data Index: 1289865 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.3525. Min Act: -0.0000

Data Index: 529589 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.3796. Min Act: -0.0000

Data Index: 1350704 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.5681. Min Range: -0.5681

Max Act: 0.3362. Min Act: -0.0000

Data Index: 338174 (C4 (Web Text))

Max Activating Token Index: 80