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

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

Neuron 1745 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.9007. Min Act: -0.0001

Data Index: 739473 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.9052. Min Act: -0.0001

Data Index: 532362 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.8631. Min Act: -0.0001

Data Index: 94016 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.8424. Min Act: -0.0001

Data Index: 595940 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.8289. Min Act: -0.0001

Data Index: 114487 (C4 (Web Text))

Max Activating Token Index: 663

Text #5

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7980. Min Act: -0.0001

Data Index: 129225 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.8005. Min Act: -0.0001

Data Index: 807195 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.8211. Min Act: -0.0001

Data Index: 862099 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7972. Min Act: -0.0001

Data Index: 754625 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7780. Min Act: -0.0001

Data Index: 657604 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7657. Min Act: -0.0001

Data Index: 538030 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7324. Min Act: -0.0001

Data Index: 285688 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7261. Min Act: -0.0001

Data Index: 28784 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7941. Min Act: -0.0001

Data Index: 225973 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7479. Min Act: -0.0000

Data Index: 784554 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7691. Min Act: -0.0001

Data Index: 160989 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7722. Min Act: -0.0001

Data Index: 1208101 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7651. Min Act: -0.0001

Data Index: 1005252 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7836. Min Act: -0.0001

Data Index: 1097267 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.9052. Min Range: -0.9052

Max Act: 0.7557. Min Act: -0.0001

Data Index: 538526 (C4 (Web Text))

Max Activating Token Index: 408