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

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

Neuron 400 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.5366. Min Act: -0.0000

Data Index: 895427 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.5424. Min Act: -0.0000

Data Index: 678119 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.5304. Min Act: -0.0000

Data Index: 342115 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.4218. Min Act: -0.0000

Data Index: 533709 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.3565. Min Act: -0.0000

Data Index: 521669 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.3642. Min Act: -0.0000

Data Index: 540550 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.3482. Min Act: -0.0000

Data Index: 252407 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.3712. Min Act: -0.0000

Data Index: 153251 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.3581. Min Act: -0.0000

Data Index: 962427 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.2982. Min Act: -0.0000

Data Index: 104606 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.3289. Min Act: -0.0000

Data Index: 439509 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.3748. Min Act: -0.0000

Data Index: 1014757 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.3128. Min Act: -0.0000

Data Index: 24647 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.3468. Min Act: -0.0000

Data Index: 1176176 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.3176. Min Act: -0.0000

Data Index: 103342 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.3158. Min Act: -0.0000

Data Index: 721399 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.3014. Min Act: -0.0000

Data Index: 263841 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.2601. Min Act: -0.0000

Data Index: 117163 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.3240. Min Act: -0.0000

Data Index: 36677 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 0.5424. Min Range: -0.5424

Max Act: 0.2928. Min Act: -0.0000

Data Index: 1355055 (C4 (Web Text))

Max Activating Token Index: 926