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

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

Neuron 621 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: 1.3599. Min Range: -1.3599

Max Act: 1.2803. Min Act: -0.0000

Data Index: 1252713 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 1.3599. Min Range: -1.3599

Max Act: 1.3599. Min Act: -0.0000

Data Index: 1119884 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 1.3599. Min Range: -1.3599

Max Act: 1.1252. Min Act: -0.0000

Data Index: 796454 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.9166. Min Act: -0.0000

Data Index: 975462 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.8247. Min Act: -0.0000

Data Index: 760173 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.8169. Min Act: -0.0000

Data Index: 950152 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.8102. Min Act: -0.0000

Data Index: 455359 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.8084. Min Act: -0.0000

Data Index: 408212 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.8240. Min Act: -0.0000

Data Index: 177974 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.8083. Min Act: -0.0000

Data Index: 1212144 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.6560. Min Act: -0.0000

Data Index: 712462 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.8200. Min Act: -0.0000

Data Index: 904327 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.7435. Min Act: -0.0000

Data Index: 942054 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.7354. Min Act: -0.0000

Data Index: 193560 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.7115. Min Act: -0.0000

Data Index: 1250414 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.7336. Min Act: -0.0000

Data Index: 903341 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.7042. Min Act: -0.0000

Data Index: 291644 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.6856. Min Act: -0.0000

Data Index: 607044 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.6879. Min Act: -0.0000

Data Index: 96493 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 1.3599. Min Range: -1.3599

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1290798 (C4 (Web Text))

Max Activating Token Index: 273