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

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

Neuron 3318 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0136. Min Range: -4.0136

Max Act: 3.9807. Min Act: -0.0000

Data Index: 243237 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 4.0136. Min Range: -4.0136

Max Act: 4.0136. Min Act: -0.0000

Data Index: 1248780 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 4.0136. Min Range: -4.0136

Max Act: 3.6768. Min Act: -0.0000

Data Index: 155411 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 4.0136. Min Range: -4.0136

Max Act: 3.7823. Min Act: -0.0000

Data Index: 878964 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 4.0136. Min Range: -4.0136

Max Act: 3.6322. Min Act: -0.0000

Data Index: 258167 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 4.0136. Min Range: -4.0136

Max Act: 3.5207. Min Act: -0.0000

Data Index: 510767 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 4.0136. Min Range: -4.0136

Max Act: 3.5954. Min Act: -0.0000

Data Index: 150322 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 4.0136. Min Range: -4.0136

Max Act: 3.5316. Min Act: -0.0000

Data Index: 125343 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 4.0136. Min Range: -4.0136

Max Act: 3.5015. Min Act: -0.0000

Data Index: 886821 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 4.0136. Min Range: -4.0136

Max Act: 3.5051. Min Act: -0.0000

Data Index: 604901 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 4.0136. Min Range: -4.0136

Max Act: 3.2141. Min Act: -0.0000

Data Index: 421505 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 4.0136. Min Range: -4.0136

Max Act: 3.2068. Min Act: -0.0000

Data Index: 1194365 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 4.0136. Min Range: -4.0136

Max Act: 3.1688. Min Act: -0.0000

Data Index: 887620 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 4.0136. Min Range: -4.0136

Max Act: 3.2797. Min Act: -0.0000

Data Index: 350207 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 4.0136. Min Range: -4.0136

Max Act: 2.9664. Min Act: -0.0000

Data Index: 1257954 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 4.0136. Min Range: -4.0136

Max Act: 3.3914. Min Act: -0.0000

Data Index: 35140 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 4.0136. Min Range: -4.0136

Max Act: 3.2335. Min Act: -0.0000

Data Index: 727474 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 4.0136. Min Range: -4.0136

Max Act: 3.2086. Min Act: -0.0000

Data Index: 91156 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 4.0136. Min Range: -4.0136

Max Act: 3.2400. Min Act: -0.0000

Data Index: 496525 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 4.0136. Min Range: -4.0136

Max Act: 3.1799. Min Act: -0.0000

Data Index: 737727 (C4 (Web Text))

Max Activating Token Index: 935