Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 353 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3687. Min Act: -0.0001

Data Index: 1648309 (Python Code)

Max Activating Token Index: 512

Text #1

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3546. Min Act: -0.0001

Data Index: 1498628 (Python Code)

Max Activating Token Index: 441

Text #2

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3444. Min Act: -0.0001

Data Index: 1611042 (Python Code)

Max Activating Token Index: 440

Text #3

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3438. Min Act: -0.0001

Data Index: 1601346 (Python Code)

Max Activating Token Index: 521

Text #4

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3438. Min Act: -0.0001

Data Index: 1539521 (Python Code)

Max Activating Token Index: 490

Text #5

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3434. Min Act: -0.0001

Data Index: 1382851 (Python Code)

Max Activating Token Index: 443

Text #6

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3421. Min Act: -0.0001

Data Index: 1644812 (Python Code)

Max Activating Token Index: 524

Text #7

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3423. Min Act: -0.0002

Data Index: 1483483 (Python Code)

Max Activating Token Index: 483

Text #8

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3365. Min Act: -0.0002

Data Index: 923278 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3352. Min Act: -0.0001

Data Index: 1472184 (Python Code)

Max Activating Token Index: 417

Text #10

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3356. Min Act: -0.0001

Data Index: 1537607 (Python Code)

Max Activating Token Index: 467

Text #11

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3347. Min Act: -0.0001

Data Index: 1487319 (Python Code)

Max Activating Token Index: 434

Text #12

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3464. Min Act: -0.0001

Data Index: 1567261 (Python Code)

Max Activating Token Index: 481

Text #13

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3344. Min Act: -0.0001

Data Index: 1438942 (Python Code)

Max Activating Token Index: 493

Text #14

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3224. Min Act: -0.0001

Data Index: 1611327 (Python Code)

Max Activating Token Index: 431

Text #15

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3340. Min Act: -0.0001

Data Index: 1498281 (Python Code)

Max Activating Token Index: 438

Text #16

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3342. Min Act: -0.0001

Data Index: 1399384 (Python Code)

Max Activating Token Index: 481

Text #17

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3336. Min Act: -0.0001

Data Index: 1366755 (Python Code)

Max Activating Token Index: 424

Text #18

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3335. Min Act: -0.0001

Data Index: 524128 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3333. Min Act: -0.0001

Data Index: 1569005 (Python Code)

Max Activating Token Index: 512