Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 653 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0793. Min Range: -2.0793

Max Act: 2.0793. Min Act: -0.0001

Data Index: 1317453 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.8116. Min Act: -0.0000

Data Index: 811293 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.8590. Min Act: -0.0001

Data Index: 777563 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.8463. Min Act: -0.0000

Data Index: 393263 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.7922. Min Act: -0.0001

Data Index: 162854 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.7710. Min Act: -0.0000

Data Index: 1283457 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.5850. Min Act: -0.0000

Data Index: 1005742 (C4 (Web Text))

Max Activating Token Index: 741

Text #7

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.5730. Min Act: -0.0000

Data Index: 1313581 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.6323. Min Act: -0.0001

Data Index: 1257632 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.6314. Min Act: -0.0000

Data Index: 555261 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.6263. Min Act: -0.0001

Data Index: 1153177 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.5014. Min Act: -0.0000

Data Index: 538655 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.4690. Min Act: -0.0001

Data Index: 1001083 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.5359. Min Act: -0.0001

Data Index: 486348 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.5332. Min Act: -0.0001

Data Index: 763171 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.5728. Min Act: -0.0000

Data Index: 184723 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.6022. Min Act: -0.0000

Data Index: 41927 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.4982. Min Act: -0.0000

Data Index: 599494 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.5438. Min Act: -0.0001

Data Index: 437985 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 2.0793. Min Range: -2.0793

Max Act: 1.6268. Min Act: -0.0001

Data Index: 998534 (C4 (Web Text))

Max Activating Token Index: 457