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

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

Neuron 1634 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: 0.0639. Min Range: -0.0639

Max Act: 0.0637. Min Act: -0.0002

Data Index: 720276 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0639. Min Act: -0.0002

Data Index: 467130 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0574. Min Act: -0.0002

Data Index: 633166 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0565. Min Act: -0.0002

Data Index: 999750 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1222451 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1656092 (Python Code)

Max Activating Token Index: 822

Text #6

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1057023 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0527. Min Act: -0.0002

Data Index: 614414 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1164329 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1615860 (Python Code)

Max Activating Token Index: 836

Text #10

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0488. Min Act: -0.0002

Data Index: 595284 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0491. Min Act: -0.0002

Data Index: 362244 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0487. Min Act: -0.0002

Data Index: 208706 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0480. Min Act: -0.0002

Data Index: 417002 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0479. Min Act: -0.0002

Data Index: 83097 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0485. Min Act: -0.0002

Data Index: 159745 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0471. Min Act: -0.0002

Data Index: 13021 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0460. Min Act: -0.0002

Data Index: 445916 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0467. Min Act: -0.0002

Data Index: 718131 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.0639. Min Range: -0.0639

Max Act: 0.0456. Min Act: -0.0002

Data Index: 217060 (C4 (Web Text))

Max Activating Token Index: 929