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

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

Neuron 4566 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: 4.9258. Min Range: -4.9258

Max Act: 4.9258. Min Act: -0.0000

Data Index: 937654 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 4.9258. Min Range: -4.9258

Max Act: 4.0210. Min Act: -0.0000

Data Index: 116649 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 4.9258. Min Range: -4.9258

Max Act: 3.9605. Min Act: -0.0000

Data Index: 843498 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 4.9258. Min Range: -4.9258

Max Act: 3.8522. Min Act: -0.0000

Data Index: 414813 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 4.9258. Min Range: -4.9258

Max Act: 3.3887. Min Act: -0.0000

Data Index: 1125900 (C4 (Web Text))

Max Activating Token Index: 609

Text #5

Max Range: 4.9258. Min Range: -4.9258

Max Act: 3.3951. Min Act: -0.0000

Data Index: 1023090 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 4.9258. Min Range: -4.9258

Max Act: 3.3959. Min Act: -0.0000

Data Index: 421667 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 4.9258. Min Range: -4.9258

Max Act: 3.4256. Min Act: -0.0000

Data Index: 262322 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 4.9258. Min Range: -4.9258

Max Act: 3.3760. Min Act: -0.0000

Data Index: 517593 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 4.9258. Min Range: -4.9258

Max Act: 3.3803. Min Act: -0.0000

Data Index: 101630 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 4.9258. Min Range: -4.9258

Max Act: 3.2364. Min Act: -0.0000

Data Index: 115407 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 4.9258. Min Range: -4.9258

Max Act: 3.1868. Min Act: -0.0000

Data Index: 933744 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 4.9258. Min Range: -4.9258

Max Act: 3.2387. Min Act: -0.0000

Data Index: 925371 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 4.9258. Min Range: -4.9258

Max Act: 2.9123. Min Act: -0.0000

Data Index: 672734 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 4.9258. Min Range: -4.9258

Max Act: 3.0369. Min Act: -0.0000

Data Index: 936307 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 4.9258. Min Range: -4.9258

Max Act: 2.8476. Min Act: -0.0000

Data Index: 340241 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 4.9258. Min Range: -4.9258

Max Act: 3.1328. Min Act: -0.0000

Data Index: 482438 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 4.9258. Min Range: -4.9258

Max Act: 3.1121. Min Act: -0.0000

Data Index: 1139089 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 4.9258. Min Range: -4.9258

Max Act: 2.9258. Min Act: -0.0000

Data Index: 1190038 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 4.9258. Min Range: -4.9258

Max Act: 2.9174. Min Act: -0.0000

Data Index: 1330219 (C4 (Web Text))

Max Activating Token Index: 314