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

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

Neuron 527 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4123. Min Range: -5.4123

Max Act: 5.4123. Min Act: -0.0000

Data Index: 283356 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 5.4123. Min Range: -5.4123

Max Act: 5.0795. Min Act: -0.0000

Data Index: 567287 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 5.4123. Min Range: -5.4123

Max Act: 5.1332. Min Act: -0.0000

Data Index: 463114 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 5.4123. Min Range: -5.4123

Max Act: 4.8889. Min Act: -0.0000

Data Index: 1203248 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 5.4123. Min Range: -5.4123

Max Act: 5.0602. Min Act: -0.0000

Data Index: 685706 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 5.4123. Min Range: -5.4123

Max Act: 5.0229. Min Act: -0.0000

Data Index: 1065620 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 5.4123. Min Range: -5.4123

Max Act: 5.2365. Min Act: -0.0000

Data Index: 738912 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 5.4123. Min Range: -5.4123

Max Act: 5.0098. Min Act: -0.0000

Data Index: 1211673 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 5.4123. Min Range: -5.4123

Max Act: 5.2204. Min Act: -0.0000

Data Index: 740247 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 5.4123. Min Range: -5.4123

Max Act: 5.0030. Min Act: -0.0000

Data Index: 45801 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 5.4123. Min Range: -5.4123

Max Act: 4.8275. Min Act: -0.0000

Data Index: 1143980 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 5.4123. Min Range: -5.4123

Max Act: 4.8515. Min Act: -0.0000

Data Index: 41673 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 5.4123. Min Range: -5.4123

Max Act: 4.9892. Min Act: -0.0000

Data Index: 177173 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 5.4123. Min Range: -5.4123

Max Act: 5.1768. Min Act: -0.0000

Data Index: 881848 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 5.4123. Min Range: -5.4123

Max Act: 4.7502. Min Act: -0.0000

Data Index: 899022 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 5.4123. Min Range: -5.4123

Max Act: 4.8899. Min Act: -0.0000

Data Index: 1147791 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 5.4123. Min Range: -5.4123

Max Act: 4.8952. Min Act: -0.0000

Data Index: 890672 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 5.4123. Min Range: -5.4123

Max Act: 4.8850. Min Act: -0.0000

Data Index: 648138 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 5.4123. Min Range: -5.4123

Max Act: 4.8636. Min Act: -0.0000

Data Index: 403594 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 5.4123. Min Range: -5.4123

Max Act: 4.8710. Min Act: -0.0000

Data Index: 351169 (C4 (Web Text))

Max Activating Token Index: 552