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

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

Neuron 334 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.6562. Min Act: -0.0001

Data Index: 498620 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.6544. Min Act: -0.0001

Data Index: 533964 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5999. Min Act: -0.0001

Data Index: 1014807 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5987. Min Act: -0.0001

Data Index: 880084 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.6016. Min Act: -0.0001

Data Index: 9111 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5962. Min Act: -0.0001

Data Index: 191912 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.6067. Min Act: -0.0001

Data Index: 885031 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5903. Min Act: -0.0001

Data Index: 574236 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5461. Min Act: -0.0001

Data Index: 507027 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5396. Min Act: -0.0001

Data Index: 1055262 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5874. Min Act: -0.0001

Data Index: 1306916 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5680. Min Act: -0.0001

Data Index: 850816 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5675. Min Act: -0.0001

Data Index: 426708 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5380. Min Act: -0.0001

Data Index: 445960 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5540. Min Act: -0.0001

Data Index: 798758 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5166. Min Act: -0.0001

Data Index: 165034 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5719. Min Act: -0.0001

Data Index: 827041 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5324. Min Act: -0.0001

Data Index: 805025 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.4956. Min Act: -0.0001

Data Index: 375537 (C4 (Web Text))

Max Activating Token Index: 4

Text #19

Max Range: 0.6562. Min Range: -0.6562

Max Act: 0.5863. Min Act: -0.0001

Data Index: 978080 (C4 (Web Text))

Max Activating Token Index: 664