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

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

Neuron 704 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0725. Min Act: -0.0002

Data Index: 937200 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0636. Min Act: -0.0002

Data Index: 163847 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1325690 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0538. Min Act: -0.0002

Data Index: 639596 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0585. Min Act: -0.0002

Data Index: 710209 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1269931 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0549. Min Act: -0.0002

Data Index: 909270 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0506. Min Act: -0.0002

Data Index: 266146 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0515. Min Act: -0.0002

Data Index: 241226 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0545. Min Act: -0.0002

Data Index: 151857 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0527. Min Act: -0.0002

Data Index: 100077 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1075848 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0514. Min Act: -0.0002

Data Index: 305933 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1225239 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0515. Min Act: -0.0002

Data Index: 1231683 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0506. Min Act: -0.0002

Data Index: 99478 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0506. Min Act: -0.0002

Data Index: 369676 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0471. Min Act: -0.0002

Data Index: 762963 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0500. Min Act: -0.0002

Data Index: 678913 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.0725. Min Range: -0.0725

Max Act: 0.0488. Min Act: -0.0002

Data Index: 388489 (C4 (Web Text))

Max Activating Token Index: 277