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

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

Neuron 4506 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7659. Min Act: -0.0000

Data Index: 472147 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7686. Min Act: -0.0000

Data Index: 114716 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1075045 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7435. Min Act: -0.0000

Data Index: 393301 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6825. Min Act: -0.0000

Data Index: 449787 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6928. Min Act: -0.0000

Data Index: 878987 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6286. Min Act: -0.0000

Data Index: 243772 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6860. Min Act: -0.0000

Data Index: 781837 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6664. Min Act: -0.0000

Data Index: 950554 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6073. Min Act: -0.0000

Data Index: 1112594 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6043. Min Act: -0.0000

Data Index: 383329 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6059. Min Act: -0.0000

Data Index: 82001 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6218. Min Act: -0.0000

Data Index: 4561 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5786. Min Act: -0.0000

Data Index: 953460 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5766. Min Act: -0.0000

Data Index: 861582 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5949. Min Act: -0.0000

Data Index: 1300827 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6077. Min Act: -0.0000

Data Index: 45757 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5865. Min Act: -0.0000

Data Index: 776010 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1097521 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5266. Min Act: -0.0000

Data Index: 48236 (C4 (Web Text))

Max Activating Token Index: 991