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

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

Neuron 718 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: 0.9393. Min Range: -0.9393

Max Act: 0.9393. Min Act: -0.0000

Data Index: 1353869 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.8930. Min Act: -0.0000

Data Index: 1200088 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.8689. Min Act: -0.0000

Data Index: 466586 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.8004. Min Act: -0.0000

Data Index: 646202 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7895. Min Act: -0.0000

Data Index: 770106 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7929. Min Act: -0.0000

Data Index: 1189553 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7867. Min Act: 0.0000

Data Index: 1337878 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7817. Min Act: -0.0000

Data Index: 719359 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7553. Min Act: -0.0000

Data Index: 248064 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7502. Min Act: -0.0000

Data Index: 597543 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7448. Min Act: -0.0000

Data Index: 16440 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7226. Min Act: -0.0000

Data Index: 121801 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7376. Min Act: -0.0000

Data Index: 57569 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7108. Min Act: -0.0000

Data Index: 1011335 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.7161. Min Act: 0.0000

Data Index: 1329077 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.6825. Min Act: -0.0000

Data Index: 67367 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.6947. Min Act: -0.0000

Data Index: 474627 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1144496 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.6912. Min Act: -0.0000

Data Index: 698099 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.9393. Min Range: -0.9393

Max Act: 0.6753. Min Act: -0.0000

Data Index: 1208405 (C4 (Web Text))

Max Activating Token Index: 940