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

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

Neuron 1293 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0484. Min Act: -0.0005

Data Index: 306578 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0473. Min Act: -0.0005

Data Index: 443142 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0445. Min Act: -0.0005

Data Index: 217838 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0431. Min Act: -0.0005

Data Index: 538592 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0341. Min Act: -0.0005

Data Index: 1491673 (Python Code)

Max Activating Token Index: 318

Text #5

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0354. Min Act: -0.0005

Data Index: 1418923 (Python Code)

Max Activating Token Index: 297

Text #6

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0333. Min Act: -0.0005

Data Index: 1167239 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0323. Min Act: -0.0005

Data Index: 733265 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0336. Min Act: -0.0005

Data Index: 1426412 (Python Code)

Max Activating Token Index: 561

Text #9

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0335. Min Act: -0.0006

Data Index: 1106438 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0334. Min Act: -0.0005

Data Index: 1380606 (Python Code)

Max Activating Token Index: 458

Text #11

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0328. Min Act: -0.0005

Data Index: 383551 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0328. Min Act: -0.0005

Data Index: 410303 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0321. Min Act: -0.0006

Data Index: 509102 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0325. Min Act: -0.0005

Data Index: 1248576 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0324. Min Act: -0.0005

Data Index: 371845 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0331. Min Act: -0.0006

Data Index: 284519 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0315. Min Act: -0.0005

Data Index: 777985 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0315. Min Act: -0.0005

Data Index: 932638 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0319. Min Act: -0.0006

Data Index: 117699 (C4 (Web Text))

Max Activating Token Index: 653