Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1394 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.5031. Min Act: -0.0000

Data Index: 347441 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.5116. Min Act: -0.0001

Data Index: 387590 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4738. Min Act: -0.0001

Data Index: 1022509 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4930. Min Act: -0.0001

Data Index: 348361 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4766. Min Act: -0.0001

Data Index: 1105767 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4805. Min Act: -0.0001

Data Index: 113411 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4470. Min Act: -0.0000

Data Index: 305630 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4431. Min Act: -0.0001

Data Index: 917608 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4528. Min Act: -0.0000

Data Index: 367978 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4466. Min Act: -0.0001

Data Index: 342678 (C4 (Web Text))

Max Activating Token Index: 761

Text #10

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4480. Min Act: -0.0000

Data Index: 140462 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4458. Min Act: -0.0000

Data Index: 855348 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4426. Min Act: -0.0001

Data Index: 649598 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4425. Min Act: -0.0000

Data Index: 709496 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4427. Min Act: -0.0001

Data Index: 928023 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4247. Min Act: -0.0001

Data Index: 563273 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4249. Min Act: -0.0001

Data Index: 1090399 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4217. Min Act: -0.0001

Data Index: 1192984 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4393. Min Act: -0.0001

Data Index: 753597 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.5116. Min Range: -0.5116

Max Act: 0.4494. Min Act: -0.0001

Data Index: 524742 (C4 (Web Text))

Max Activating Token Index: 276