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

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

Neuron 1425 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4509. Min Act: -0.0002

Data Index: 1419463 (Python Code)

Max Activating Token Index: 286

Text #1

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4288. Min Act: -0.0002

Data Index: 1379206 (Python Code)

Max Activating Token Index: 292

Text #2

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4386. Min Act: -0.0002

Data Index: 1643238 (Python Code)

Max Activating Token Index: 450

Text #3

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4182. Min Act: -0.0002

Data Index: 1616517 (Python Code)

Max Activating Token Index: 243

Text #4

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4043. Min Act: -0.0002

Data Index: 1656805 (Python Code)

Max Activating Token Index: 448

Text #5

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4156. Min Act: -0.0002

Data Index: 1599222 (Python Code)

Max Activating Token Index: 319

Text #6

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4130. Min Act: -0.0002

Data Index: 1431486 (Python Code)

Max Activating Token Index: 232

Text #7

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4111. Min Act: -0.0002

Data Index: 1471323 (Python Code)

Max Activating Token Index: 204

Text #8

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.4050. Min Act: -0.0002

Data Index: 1594451 (Python Code)

Max Activating Token Index: 272

Text #9

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3924. Min Act: -0.0002

Data Index: 1447045 (Python Code)

Max Activating Token Index: 692

Text #10

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3948. Min Act: -0.0002

Data Index: 1448396 (Python Code)

Max Activating Token Index: 538

Text #11

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3936. Min Act: -0.0002

Data Index: 1415060 (Python Code)

Max Activating Token Index: 287

Text #12

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3824. Min Act: -0.0002

Data Index: 1490117 (Python Code)

Max Activating Token Index: 40

Text #13

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3894. Min Act: -0.0002

Data Index: 1557901 (Python Code)

Max Activating Token Index: 262

Text #14

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3865. Min Act: -0.0002

Data Index: 1545382 (Python Code)

Max Activating Token Index: 265

Text #15

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3817. Min Act: -0.0002

Data Index: 1489590 (Python Code)

Max Activating Token Index: 436

Text #16

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3785. Min Act: -0.0002

Data Index: 1518683 (Python Code)

Max Activating Token Index: 463

Text #17

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3868. Min Act: -0.0002

Data Index: 1629298 (Python Code)

Max Activating Token Index: 715

Text #18

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3866. Min Act: -0.0002

Data Index: 1528171 (Python Code)

Max Activating Token Index: 607

Text #19

Max Range: 0.4509. Min Range: -0.4509

Max Act: 0.3809. Min Act: -0.0002

Data Index: 1616312 (Python Code)

Max Activating Token Index: 184