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

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

Neuron 5958 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.1412. Min Act: -0.0000

Data Index: 242702 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.2839. Min Act: -0.0000

Data Index: 1023290 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.2374. Min Act: -0.0000

Data Index: 1190356 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.2638. Min Act: -0.0000

Data Index: 92033 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.1973. Min Act: -0.0000

Data Index: 163779 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.2453. Min Act: -0.0000

Data Index: 672822 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.1726. Min Act: -0.0000

Data Index: 868436 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.0557. Min Act: -0.0000

Data Index: 1266044 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.1032. Min Act: -0.0000

Data Index: 521216 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.2184. Min Act: -0.0000

Data Index: 771261 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.1271. Min Act: -0.0000

Data Index: 704111 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.1113. Min Act: -0.0000

Data Index: 814201 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.1054. Min Act: -0.0000

Data Index: 1036081 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.0952. Min Act: -0.0000

Data Index: 240242 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.0870. Min Act: -0.0000

Data Index: 623140 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.0049. Min Act: -0.0000

Data Index: 1351627 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 1.2839. Min Range: -1.2839

Max Act: 0.9991. Min Act: -0.0000

Data Index: 176726 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 1.2839. Min Range: -1.2839

Max Act: 1.0285. Min Act: -0.0000

Data Index: 255617 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 1.2839. Min Range: -1.2839

Max Act: 0.9370. Min Act: -0.0000

Data Index: 690838 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 1.2839. Min Range: -1.2839

Max Act: 0.9928. Min Act: -0.0000

Data Index: 376969 (C4 (Web Text))

Max Activating Token Index: 585