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

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

Neuron 2355 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.0492. Min Act: -0.0004

Data Index: 1230485 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.0607. Min Act: -0.0004

Data Index: 649632 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.1762. Min Act: -0.0004

Data Index: 402572 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9791. Min Act: -0.0004

Data Index: 1137103 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9512. Min Act: -0.0004

Data Index: 1228537 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.1890. Min Act: -0.0004

Data Index: 545101 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.0465. Min Act: -0.0004

Data Index: 574276 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.1522. Min Act: -0.0004

Data Index: 1044181 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.0905. Min Act: -0.0004

Data Index: 1920 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.7268. Min Act: -0.0004

Data Index: 370214 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.1869. Min Act: -0.0004

Data Index: 1245326 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.7813. Min Act: -0.0004

Data Index: 1009538 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9564. Min Act: -0.0004

Data Index: 783846 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.0657. Min Act: -0.0004

Data Index: 1056527 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.0674. Min Act: -0.0004

Data Index: 1141848 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.0272. Min Act: -0.0004

Data Index: 257623 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.0910. Min Act: -0.0004

Data Index: 578718 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9968. Min Act: -0.0004

Data Index: 604784 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9955. Min Act: -0.0004

Data Index: 411182 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.0202. Min Act: -0.0004

Data Index: 621100 (C4 (Web Text))

Max Activating Token Index: 997