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

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

Neuron 2913 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: 0.0535. Min Range: -0.0535

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1071095 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0535. Min Act: -0.0001

Data Index: 1343132 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0446. Min Act: -0.0000

Data Index: 421916 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0465. Min Act: -0.0001

Data Index: 133926 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0513. Min Act: -0.0000

Data Index: 465706 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1294374 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0450. Min Act: -0.0001

Data Index: 1354119 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0456. Min Act: -0.0001

Data Index: 1175101 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0424. Min Act: -0.0001

Data Index: 1308869 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0449. Min Act: -0.0001

Data Index: 860917 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0404. Min Act: -0.0001

Data Index: 1559836 (Python Code)

Max Activating Token Index: 615

Text #11

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0413. Min Act: -0.0001

Data Index: 1324839 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1017891 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0425. Min Act: -0.0000

Data Index: 1358652 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0424. Min Act: -0.0001

Data Index: 1030787 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0420. Min Act: -0.0001

Data Index: 974737 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0387. Min Act: -0.0001

Data Index: 26835 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0414. Min Act: -0.0000

Data Index: 821274 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0410. Min Act: -0.0000

Data Index: 419016 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 0.0535. Min Range: -0.0535

Max Act: 0.0425. Min Act: -0.0000

Data Index: 339839 (C4 (Web Text))

Max Activating Token Index: 365