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

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

Neuron 3629 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4985. Min Range: -1.4985

Max Act: 1.4985. Min Act: -0.0000

Data Index: 891578 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 1.4985. Min Range: -1.4985

Max Act: 1.3480. Min Act: -0.0000

Data Index: 567665 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 1.4985. Min Range: -1.4985

Max Act: 1.1658. Min Act: -0.0001

Data Index: 519363 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 1.4985. Min Range: -1.4985

Max Act: 1.1028. Min Act: -0.0000

Data Index: 1269944 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 1.4985. Min Range: -1.4985

Max Act: 1.0882. Min Act: -0.0000

Data Index: 943420 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 1.4985. Min Range: -1.4985

Max Act: 1.1383. Min Act: -0.0000

Data Index: 759734 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 1.4985. Min Range: -1.4985

Max Act: 1.1021. Min Act: -0.0001

Data Index: 567701 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 1.4985. Min Range: -1.4985

Max Act: 1.0420. Min Act: -0.0000

Data Index: 106397 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 1.4985. Min Range: -1.4985

Max Act: 0.9524. Min Act: -0.0000

Data Index: 900474 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 1.4985. Min Range: -1.4985

Max Act: 0.9807. Min Act: -0.0001

Data Index: 19071 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 1.4985. Min Range: -1.4985

Max Act: 1.0274. Min Act: -0.0001

Data Index: 501157 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 1.4985. Min Range: -1.4985

Max Act: 0.9422. Min Act: -0.0001

Data Index: 103255 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 1.4985. Min Range: -1.4985

Max Act: 0.9538. Min Act: -0.0000

Data Index: 8593 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 1.4985. Min Range: -1.4985

Max Act: 0.9102. Min Act: -0.0000

Data Index: 262594 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 1.4985. Min Range: -1.4985

Max Act: 0.9367. Min Act: -0.0000

Data Index: 857922 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 1.4985. Min Range: -1.4985

Max Act: 0.9589. Min Act: -0.0000

Data Index: 53604 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 1.4985. Min Range: -1.4985

Max Act: 0.8710. Min Act: -0.0001

Data Index: 1338301 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 1.4985. Min Range: -1.4985

Max Act: 0.8107. Min Act: -0.0000

Data Index: 193039 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 1.4985. Min Range: -1.4985

Max Act: 0.9124. Min Act: -0.0001

Data Index: 630270 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 1.4985. Min Range: -1.4985

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1109201 (C4 (Web Text))

Max Activating Token Index: 825