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

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

Neuron 1872 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.2117. Min Act: -0.0000

Data Index: 695530 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.2835. Min Act: -0.0000

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.1004. Min Act: -0.0000

Data Index: 364476 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 3.2835. Min Range: -3.2835

Max Act: 3.0528. Min Act: -0.0000

Data Index: 593230 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.3895. Min Act: -0.0000

Data Index: 959952 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.0831. Min Act: -0.0000

Data Index: 1065047 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 3.2835. Min Range: -3.2835

Max Act: 1.9615. Min Act: -0.0000

Data Index: 444625 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.1416. Min Act: -0.0000

Data Index: 113182 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 3.2835. Min Range: -3.2835

Max Act: 1.9026. Min Act: -0.0000

Data Index: 117969 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.0154. Min Act: -0.0000

Data Index: 494804 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 3.2835. Min Range: -3.2835

Max Act: 1.7509. Min Act: -0.0000

Data Index: 482320 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 3.2835. Min Range: -3.2835

Max Act: 1.8523. Min Act: -0.0000

Data Index: 437884 (C4 (Web Text))

Max Activating Token Index: 172

Text #12

Max Range: 3.2835. Min Range: -3.2835

Max Act: 1.8544. Min Act: -0.0000

Data Index: 1047528 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 3.2835. Min Range: -3.2835

Max Act: 1.9476. Min Act: -0.0000

Data Index: 1167311 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 3.2835. Min Range: -3.2835

Max Act: 1.9332. Min Act: -0.0000

Data Index: 622901 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 3.2835. Min Range: -3.2835

Max Act: 2.0283. Min Act: -0.0000

Data Index: 667758 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 3.2835. Min Range: -3.2835

Max Act: 1.7894. Min Act: -0.0000

Data Index: 1307031 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 3.2835. Min Range: -3.2835

Max Act: 1.7939. Min Act: -0.0000

Data Index: 38461 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 3.2835. Min Range: -3.2835

Max Act: 1.7527. Min Act: -0.0000

Data Index: 1044344 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 3.2835. Min Range: -3.2835

Max Act: 1.7256. Min Act: -0.0000

Data Index: 123797 (C4 (Web Text))

Max Activating Token Index: 45