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

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

Neuron 4820 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1961. Min Range: -1.1961

Max Act: 1.1961. Min Act: 0.0001

Data Index: 1059979 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 1.1961. Min Range: -1.1961

Max Act: 1.0699. Min Act: 0.0001

Data Index: 342811 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.9546. Min Act: -0.0000

Data Index: 1097113 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.9743. Min Act: -0.0000

Data Index: 1018817 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8815. Min Act: -0.0000

Data Index: 563914 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8983. Min Act: -0.0000

Data Index: 917307 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.9380. Min Act: 0.0000

Data Index: 456937 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.9217. Min Act: -0.0000

Data Index: 806362 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8611. Min Act: -0.0000

Data Index: 276987 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1175510 (C4 (Web Text))

Max Activating Token Index: 30

Text #10

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1132626 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1234693 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8455. Min Act: -0.0000

Data Index: 1010482 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1228857 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1141857 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8099. Min Act: -0.0000

Data Index: 764383 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.8349. Min Act: -0.0000

Data Index: 261283 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.7718. Min Act: -0.0000

Data Index: 1312855 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.7705. Min Act: -0.0000

Data Index: 509195 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 1.1961. Min Range: -1.1961

Max Act: 0.7588. Min Act: -0.0000

Data Index: 45035 (C4 (Web Text))

Max Activating Token Index: 951