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

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

Neuron 1239 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0451. Min Act: -0.0001

Data Index: 707759 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0482. Min Act: -0.0001

Data Index: 102944 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0459. Min Act: -0.0001

Data Index: 1055758 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0453. Min Act: -0.0001

Data Index: 211958 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0464. Min Act: -0.0001

Data Index: 962836 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0410. Min Act: -0.0001

Data Index: 529363 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0426. Min Act: -0.0001

Data Index: 630185 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0456. Min Act: -0.0001

Data Index: 1100400 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0435. Min Act: -0.0001

Data Index: 924810 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0425. Min Act: -0.0001

Data Index: 549216 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0450. Min Act: -0.0001

Data Index: 690023 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0416. Min Act: -0.0001

Data Index: 1289277 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0430. Min Act: -0.0001

Data Index: 1303909 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0411. Min Act: -0.0001

Data Index: 223651 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0413. Min Act: -0.0001

Data Index: 703558 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0417. Min Act: -0.0001

Data Index: 1290283 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0440. Min Act: -0.0001

Data Index: 873589 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0439. Min Act: -0.0001

Data Index: 889627 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0408. Min Act: -0.0001

Data Index: 719142 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0412. Min Act: -0.0001

Data Index: 345077 (C4 (Web Text))

Max Activating Token Index: 331