Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 848 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0667. Min Act: -0.0006

Data Index: 289388 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0631. Min Act: -0.0006

Data Index: 111834 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0542. Min Act: -0.0006

Data Index: 1451931 (Python Code)

Max Activating Token Index: 513

Text #3

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0576. Min Act: -0.0006

Data Index: 1574033 (Python Code)

Max Activating Token Index: 136

Text #4

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0575. Min Act: -0.0006

Data Index: 1055082 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0553. Min Act: -0.0006

Data Index: 298935 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0554. Min Act: -0.0006

Data Index: 1458277 (Python Code)

Max Activating Token Index: 307

Text #7

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0552. Min Act: -0.0005

Data Index: 625332 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0543. Min Act: -0.0005

Data Index: 566759 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0516. Min Act: -0.0006

Data Index: 1294652 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0528. Min Act: -0.0006

Data Index: 755800 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0519. Min Act: -0.0006

Data Index: 715241 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0527. Min Act: -0.0006

Data Index: 526379 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0503. Min Act: -0.0006

Data Index: 134256 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0521. Min Act: -0.0006

Data Index: 3720 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0501. Min Act: -0.0006

Data Index: 1249960 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0512. Min Act: -0.0006

Data Index: 1059553 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0505. Min Act: -0.0006

Data Index: 1166498 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0505. Min Act: -0.0006

Data Index: 742162 (C4 (Web Text))

Max Activating Token Index: 947

Text #19

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0516. Min Act: -0.0006

Data Index: 104244 (C4 (Web Text))

Max Activating Token Index: 14