Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3287 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.1046. Min Act: -0.0000

Data Index: 268955 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0825. Min Act: -0.0000

Data Index: 1375700 (Python Code)

Max Activating Token Index: 754

Text #2

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0873. Min Act: -0.0000

Data Index: 1455043 (Python Code)

Max Activating Token Index: 774

Text #3

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1588777 (Python Code)

Max Activating Token Index: 1015

Text #4

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0663. Min Act: -0.0000

Data Index: 1388072 (Python Code)

Max Activating Token Index: 539

Text #5

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0680. Min Act: -0.0000

Data Index: 47588 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0672. Min Act: -0.0000

Data Index: 1120859 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0618. Min Act: -0.0000

Data Index: 438697 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0627. Min Act: -0.0000

Data Index: 1270988 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0609. Min Act: -0.0000

Data Index: 407174 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0604. Min Act: -0.0000

Data Index: 1518466 (Python Code)

Max Activating Token Index: 719

Text #11

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0625. Min Act: -0.0000

Data Index: 1649815 (Python Code)

Max Activating Token Index: 496

Text #12

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0621. Min Act: -0.0000

Data Index: 1185352 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0617. Min Act: -0.0000

Data Index: 1446304 (Python Code)

Max Activating Token Index: 739

Text #14

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0611. Min Act: -0.0000

Data Index: 1500096 (Python Code)

Max Activating Token Index: 513

Text #15

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0593. Min Act: -0.0000

Data Index: 1361409 (Python Code)

Max Activating Token Index: 431

Text #16

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1443894 (Python Code)

Max Activating Token Index: 253

Text #17

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0607. Min Act: -0.0000

Data Index: 200351 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0545. Min Act: -0.0000

Data Index: 1435927 (Python Code)

Max Activating Token Index: 277

Text #19

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1218293 (C4 (Web Text))

Max Activating Token Index: 840