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

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

Neuron 5218 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: 0.0567. Min Range: -0.0567

Max Act: 0.0567. Min Act: -0.0002

Data Index: 6004 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0546. Min Act: -0.0002

Data Index: 350400 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0549. Min Act: -0.0002

Data Index: 795816 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1239909 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0516. Min Act: -0.0002

Data Index: 214863 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0525. Min Act: -0.0002

Data Index: 510943 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0519. Min Act: -0.0002

Data Index: 852952 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0515. Min Act: -0.0002

Data Index: 607284 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0517. Min Act: -0.0002

Data Index: 514638 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0524. Min Act: -0.0002

Data Index: 442146 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0502. Min Act: -0.0002

Data Index: 856170 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0490. Min Act: -0.0002

Data Index: 809334 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1537044 (Python Code)

Max Activating Token Index: 433

Text #13

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0497. Min Act: -0.0002

Data Index: 15016 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1288653 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0496. Min Act: -0.0002

Data Index: 535924 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1102418 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0488. Min Act: -0.0002

Data Index: 184738 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0487. Min Act: -0.0002

Data Index: 306900 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0473. Min Act: -0.0002

Data Index: 9864 (C4 (Web Text))

Max Activating Token Index: 219