Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 662 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0425. Min Act: -0.0005

Data Index: 440666 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0362. Min Act: -0.0005

Data Index: 23878 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0343. Min Act: -0.0005

Data Index: 398627 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0344. Min Act: -0.0005

Data Index: 387428 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0350. Min Act: -0.0005

Data Index: 913091 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0326. Min Act: -0.0005

Data Index: 381025 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0332. Min Act: -0.0005

Data Index: 1215776 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0308. Min Act: -0.0005

Data Index: 480935 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0318. Min Act: -0.0005

Data Index: 779631 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0328. Min Act: -0.0005

Data Index: 863247 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0314. Min Act: -0.0005

Data Index: 722010 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0321. Min Act: -0.0005

Data Index: 558323 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0310. Min Act: -0.0005

Data Index: 1605986 (Python Code)

Max Activating Token Index: 717

Text #13

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0311. Min Act: -0.0005

Data Index: 73316 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0313. Min Act: -0.0005

Data Index: 1580583 (Python Code)

Max Activating Token Index: 793

Text #15

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0311. Min Act: -0.0005

Data Index: 1598341 (Python Code)

Max Activating Token Index: 419

Text #16

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0300. Min Act: -0.0005

Data Index: 1106304 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0319. Min Act: -0.0005

Data Index: 713619 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0328. Min Act: -0.0005

Data Index: 1073602 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.0425. Min Range: -0.0425

Max Act: 0.0319. Min Act: -0.0005

Data Index: 383970 (C4 (Web Text))

Max Activating Token Index: 591