Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2300 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0793. Min Act: -0.0003

Data Index: 765244 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0703. Min Act: -0.0003

Data Index: 855088 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0713. Min Act: -0.0003

Data Index: 902639 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0730. Min Act: -0.0003

Data Index: 1581323 (Python Code)

Max Activating Token Index: 345

Text #4

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0696. Min Act: -0.0003

Data Index: 442846 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0715. Min Act: -0.0003

Data Index: 896944 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0679. Min Act: -0.0003

Data Index: 1243827 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0689. Min Act: -0.0003

Data Index: 926034 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0685. Min Act: -0.0003

Data Index: 1556547 (Python Code)

Max Activating Token Index: 188

Text #9

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0697. Min Act: -0.0003

Data Index: 913324 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0682. Min Act: -0.0003

Data Index: 1292982 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0631. Min Act: -0.0003

Data Index: 1488856 (Python Code)

Max Activating Token Index: 267

Text #12

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1591355 (Python Code)

Max Activating Token Index: 240

Text #13

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0644. Min Act: -0.0003

Data Index: 433581 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0664. Min Act: -0.0003

Data Index: 1270116 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0677. Min Act: -0.0003

Data Index: 880953 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0655. Min Act: -0.0003

Data Index: 929911 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0643. Min Act: -0.0003

Data Index: 1431220 (Python Code)

Max Activating Token Index: 287

Text #18

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0653. Min Act: -0.0003

Data Index: 94298 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.0793. Min Range: -0.0793

Max Act: 0.0652. Min Act: -0.0003

Data Index: 1631016 (Python Code)

Max Activating Token Index: 318