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

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

Neuron 4916 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: 7.3012. Min Range: -7.3012

Max Act: 7.3012. Min Act: -0.0000

Data Index: 590568 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 7.3012. Min Range: -7.3012

Max Act: 7.0936. Min Act: -0.0000

Data Index: 895115 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 7.3012. Min Range: -7.3012

Max Act: 6.8749. Min Act: -0.0000

Data Index: 43248 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 7.3012. Min Range: -7.3012

Max Act: 6.8380. Min Act: -0.0000

Data Index: 384990 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 7.3012. Min Range: -7.3012

Max Act: 6.5331. Min Act: -0.0000

Data Index: 538524 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 7.3012. Min Range: -7.3012

Max Act: 6.2770. Min Act: -0.0000

Data Index: 913246 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 7.3012. Min Range: -7.3012

Max Act: 6.0153. Min Act: -0.0000

Data Index: 1018197 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 7.3012. Min Range: -7.3012

Max Act: 6.1297. Min Act: -0.0000

Data Index: 1289484 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 7.3012. Min Range: -7.3012

Max Act: 6.1371. Min Act: -0.0000

Data Index: 238024 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 7.3012. Min Range: -7.3012

Max Act: 5.9666. Min Act: -0.0000

Data Index: 323132 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 7.3012. Min Range: -7.3012

Max Act: 5.9412. Min Act: -0.0000

Data Index: 395 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 7.3012. Min Range: -7.3012

Max Act: 5.9217. Min Act: -0.0000

Data Index: 292230 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 7.3012. Min Range: -7.3012

Max Act: 5.8302. Min Act: -0.0000

Data Index: 1110165 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 7.3012. Min Range: -7.3012

Max Act: 5.8259. Min Act: -0.0000

Data Index: 711630 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 7.3012. Min Range: -7.3012

Max Act: 6.0000. Min Act: -0.0000

Data Index: 1316575 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 7.3012. Min Range: -7.3012

Max Act: 5.7895. Min Act: -0.0000

Data Index: 294526 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 7.3012. Min Range: -7.3012

Max Act: 5.5783. Min Act: -0.0000

Data Index: 823219 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 7.3012. Min Range: -7.3012

Max Act: 5.7631. Min Act: -0.0000

Data Index: 253895 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 7.3012. Min Range: -7.3012

Max Act: 5.9898. Min Act: -0.0000

Data Index: 298331 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 7.3012. Min Range: -7.3012

Max Act: 5.5415. Min Act: -0.0000

Data Index: 579381 (C4 (Web Text))

Max Activating Token Index: 310