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

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

Neuron 4994 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.4433. Min Act: -0.0000

Data Index: 32731 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.4022. Min Act: -0.0000

Data Index: 132439 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.3157. Min Act: -0.0000

Data Index: 1102858 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.3006. Min Act: -0.0000

Data Index: 1622527 (Python Code)

Max Activating Token Index: 996

Text #4

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.1591. Min Act: -0.0000

Data Index: 503735 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.2033. Min Act: -0.0000

Data Index: 604470 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.1535. Min Act: -0.0000

Data Index: 257046 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.2070. Min Act: -0.0000

Data Index: 1050139 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.1972. Min Act: -0.0000

Data Index: 367541 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.0487. Min Act: -0.0000

Data Index: 850341 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1361638 (Python Code)

Max Activating Token Index: 832

Text #11

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.1058. Min Act: -0.0000

Data Index: 1637370 (Python Code)

Max Activating Token Index: 787

Text #12

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.0598. Min Act: -0.0000

Data Index: 44279 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.0880. Min Act: -0.0000

Data Index: 1540594 (Python Code)

Max Activating Token Index: 915

Text #14

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.0471. Min Act: -0.0000

Data Index: 1403047 (Python Code)

Max Activating Token Index: 968

Text #15

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.0261. Min Act: -0.0000

Data Index: 971666 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.1400. Min Act: -0.0000

Data Index: 1309305 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.0642. Min Act: -0.0000

Data Index: 250173 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.0596. Min Act: -0.0000

Data Index: 1430937 (Python Code)

Max Activating Token Index: 718

Text #19

Max Range: 1.4433. Min Range: -1.4433

Max Act: 1.0452. Min Act: -0.0000

Data Index: 122102 (C4 (Web Text))

Max Activating Token Index: 231