Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3816 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.0586. Min Range: -2.0586

Max Act: 2.0586. Min Act: -0.0000

Data Index: 213782 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 2.0586. Min Range: -2.0586

Max Act: 1.9054. Min Act: -0.0000

Data Index: 341913 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 2.0586. Min Range: -2.0586

Max Act: 1.7024. Min Act: -0.0001

Data Index: 1141793 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 2.0586. Min Range: -2.0586

Max Act: 1.7697. Min Act: -0.0000

Data Index: 254598 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 2.0586. Min Range: -2.0586

Max Act: 1.7322. Min Act: -0.0000

Data Index: 919159 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 2.0586. Min Range: -2.0586

Max Act: 1.6879. Min Act: -0.0000

Data Index: 731394 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 2.0586. Min Range: -2.0586

Max Act: 1.6875. Min Act: -0.0000

Data Index: 138678 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 2.0586. Min Range: -2.0586

Max Act: 1.5537. Min Act: -0.0000

Data Index: 51074 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 2.0586. Min Range: -2.0586

Max Act: 1.4344. Min Act: -0.0000

Data Index: 426048 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 2.0586. Min Range: -2.0586

Max Act: 1.4371. Min Act: -0.0000

Data Index: 93975 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 2.0586. Min Range: -2.0586

Max Act: 1.4053. Min Act: -0.0000

Data Index: 99548 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 2.0586. Min Range: -2.0586

Max Act: 1.3493. Min Act: -0.0001

Data Index: 88512 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 2.0586. Min Range: -2.0586

Max Act: 1.2603. Min Act: -0.0000

Data Index: 609121 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 2.0586. Min Range: -2.0586

Max Act: 1.2738. Min Act: -0.0000

Data Index: 133023 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 2.0586. Min Range: -2.0586

Max Act: 1.2652. Min Act: -0.0000

Data Index: 665666 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 2.0586. Min Range: -2.0586

Max Act: 1.2650. Min Act: -0.0000

Data Index: 996957 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 2.0586. Min Range: -2.0586

Max Act: 1.2310. Min Act: -0.0000

Data Index: 753299 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 2.0586. Min Range: -2.0586

Max Act: 1.2500. Min Act: -0.0001

Data Index: 960560 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 2.0586. Min Range: -2.0586

Max Act: 1.2445. Min Act: -0.0001

Data Index: 92228 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 2.0586. Min Range: -2.0586

Max Act: 1.2225. Min Act: -0.0001

Data Index: 1113020 (C4 (Web Text))

Max Activating Token Index: 704