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

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

Neuron 3313 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.3334. Min Act: -0.0000

Data Index: 790208 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1338056 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.3214. Min Act: -0.0000

Data Index: 150744 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.3069. Min Act: -0.0000

Data Index: 1166601 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1260375 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.2928. Min Act: -0.0000

Data Index: 1064189 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.2958. Min Act: -0.0000

Data Index: 966960 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.2852. Min Act: -0.0000

Data Index: 44052 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.2813. Min Act: -0.0000

Data Index: 663479 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.2903. Min Act: -0.0000

Data Index: 1263903 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.2893. Min Act: -0.0000

Data Index: 879695 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.2771. Min Act: -0.0000

Data Index: 561123 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1147985 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.2707. Min Act: -0.0000

Data Index: 977469 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.2515. Min Act: -0.0000

Data Index: 180268 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.2382. Min Act: -0.0000

Data Index: 15181 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.2603. Min Act: -0.0000

Data Index: 3247 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.2506. Min Act: -0.0000

Data Index: 214264 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.2494. Min Act: -0.0000

Data Index: 613105 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.3334. Min Range: -0.3334

Max Act: 0.2407. Min Act: -0.0000

Data Index: 513900 (C4 (Web Text))

Max Activating Token Index: 557