Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 650 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1339428 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0559. Min Act: -0.0003

Data Index: 461170 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0552. Min Act: -0.0003

Data Index: 722596 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0526. Min Act: -0.0004

Data Index: 1285164 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0525. Min Act: -0.0003

Data Index: 185743 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0518. Min Act: -0.0004

Data Index: 1165468 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1180821 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1272861 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0486. Min Act: -0.0003

Data Index: 970175 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0493. Min Act: -0.0003

Data Index: 851851 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0502. Min Act: -0.0003

Data Index: 297543 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0495. Min Act: -0.0002

Data Index: 475085 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0494. Min Act: -0.0003

Data Index: 811097 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0493. Min Act: -0.0003

Data Index: 838794 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0492. Min Act: -0.0003

Data Index: 265344 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0465. Min Act: -0.0004

Data Index: 345538 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0460. Min Act: -0.0003

Data Index: 1353072 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0466. Min Act: -0.0003

Data Index: 1300771 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0471. Min Act: -0.0003

Data Index: 717174 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0465. Min Act: -0.0003

Data Index: 374614 (C4 (Web Text))

Max Activating Token Index: 879