Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1336 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9093. Min Range: -2.9093

Max Act: 2.9093. Min Act: -0.0000

Data Index: 81157 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 2.9093. Min Range: -2.9093

Max Act: 2.8959. Min Act: -0.0000

Data Index: 75594 (C4 (Web Text))

Max Activating Token Index: 976

Text #2

Max Range: 2.9093. Min Range: -2.9093

Max Act: 2.5616. Min Act: -0.0000

Data Index: 104719 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 2.9093. Min Range: -2.9093

Max Act: 2.5185. Min Act: -0.0000

Data Index: 250398 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 2.9093. Min Range: -2.9093

Max Act: 2.5917. Min Act: -0.0000

Data Index: 682588 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 2.9093. Min Range: -2.9093

Max Act: 2.5966. Min Act: -0.0000

Data Index: 67500 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 2.9093. Min Range: -2.9093

Max Act: 2.4548. Min Act: -0.0000

Data Index: 1165987 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 2.9093. Min Range: -2.9093

Max Act: 2.4260. Min Act: -0.0000

Data Index: 615385 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 2.9093. Min Range: -2.9093

Max Act: 2.3389. Min Act: -0.0000

Data Index: 751922 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 2.9093. Min Range: -2.9093

Max Act: 2.3310. Min Act: -0.0000

Data Index: 329860 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 2.9093. Min Range: -2.9093

Max Act: 2.2785. Min Act: -0.0000

Data Index: 1236068 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 2.9093. Min Range: -2.9093

Max Act: 2.0128. Min Act: -0.0000

Data Index: 255977 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 2.9093. Min Range: -2.9093

Max Act: 2.1505. Min Act: -0.0000

Data Index: 1126786 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 2.9093. Min Range: -2.9093

Max Act: 1.9486. Min Act: -0.0000

Data Index: 189417 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 2.9093. Min Range: -2.9093

Max Act: 1.8095. Min Act: -0.0000

Data Index: 803470 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 2.9093. Min Range: -2.9093

Max Act: 2.1499. Min Act: -0.0000

Data Index: 1326270 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 2.9093. Min Range: -2.9093

Max Act: 1.9602. Min Act: -0.0000

Data Index: 1133454 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 2.9093. Min Range: -2.9093

Max Act: 2.0015. Min Act: -0.0000

Data Index: 18336 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 2.9093. Min Range: -2.9093

Max Act: 1.7746. Min Act: -0.0000

Data Index: 582223 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 2.9093. Min Range: -2.9093

Max Act: 1.7728. Min Act: -0.0000

Data Index: 433715 (C4 (Web Text))

Max Activating Token Index: 874