Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 427 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1124482 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0676. Min Act: -0.0001

Data Index: 571660 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1209042 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0639. Min Act: -0.0002

Data Index: 299379 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0697. Min Act: -0.0001

Data Index: 165924 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1106712 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0648. Min Act: -0.0001

Data Index: 93924 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0632. Min Act: -0.0001

Data Index: 366532 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1061783 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0601. Min Act: -0.0002

Data Index: 186216 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0611. Min Act: -0.0001

Data Index: 1323913 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0632. Min Act: -0.0001

Data Index: 1037135 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0584. Min Act: -0.0001

Data Index: 824182 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0573. Min Act: -0.0001

Data Index: 643227 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1226993 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0568. Min Act: -0.0001

Data Index: 608168 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1187213 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0576. Min Act: -0.0002

Data Index: 745322 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0580. Min Act: -0.0002

Data Index: 165239 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0571. Min Act: -0.0002

Data Index: 948046 (C4 (Web Text))

Max Activating Token Index: 950