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

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

Neuron 3162 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.7067. Min Act: -0.0001

Data Index: 734200 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.5374. Min Act: -0.0001

Data Index: 252559 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.5849. Min Act: -0.0001

Data Index: 614911 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.5494. Min Act: -0.0001

Data Index: 763649 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.4582. Min Act: -0.0001

Data Index: 1617899 (Python Code)

Max Activating Token Index: 417

Text #5

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.4803. Min Act: -0.0001

Data Index: 1175722 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.3789. Min Act: -0.0001

Data Index: 337432 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.3650. Min Act: -0.0001

Data Index: 763390 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.3140. Min Act: -0.0001

Data Index: 309734 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.3474. Min Act: -0.0001

Data Index: 649590 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.1943. Min Act: -0.0001

Data Index: 795890 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.3436. Min Act: -0.0001

Data Index: 997022 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.3829. Min Act: -0.0001

Data Index: 48791 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.3092. Min Act: -0.0001

Data Index: 116116 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.4471. Min Act: -0.0001

Data Index: 337509 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.3133. Min Act: -0.0001

Data Index: 600940 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.3597. Min Act: -0.0001

Data Index: 1378275 (Python Code)

Max Activating Token Index: 60

Text #17

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.1123. Min Act: -0.0001

Data Index: 1399033 (Python Code)

Max Activating Token Index: 276

Text #18

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.2585. Min Act: -0.0001

Data Index: 646877 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 1.7067. Min Range: -1.7067

Max Act: 1.2030. Min Act: -0.0001

Data Index: 1491434 (Python Code)

Max Activating Token Index: 23