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

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

Neuron 56 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.2657. Min Act: -0.0001

Data Index: 1571581 (Python Code)

Max Activating Token Index: 131

Text #1

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1701. Min Act: -0.0001

Data Index: 175792 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1663. Min Act: -0.0000

Data Index: 619628 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1275. Min Act: -0.0001

Data Index: 1362971 (Python Code)

Max Activating Token Index: 271

Text #4

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1498. Min Act: -0.0001

Data Index: 1416484 (Python Code)

Max Activating Token Index: 257

Text #5

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1542. Min Act: -0.0001

Data Index: 1588244 (Python Code)

Max Activating Token Index: 380

Text #6

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1435. Min Act: -0.0001

Data Index: 766885 (C4 (Web Text))

Max Activating Token Index: 131

Text #7

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1547. Min Act: -0.0001

Data Index: 800991 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1518. Min Act: -0.0001

Data Index: 1609652 (Python Code)

Max Activating Token Index: 543

Text #9

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1395. Min Act: -0.0001

Data Index: 1633812 (Python Code)

Max Activating Token Index: 652

Text #10

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1450. Min Act: -0.0001

Data Index: 1516762 (Python Code)

Max Activating Token Index: 376

Text #11

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1402. Min Act: -0.0001

Data Index: 1635925 (Python Code)

Max Activating Token Index: 394

Text #12

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1438. Min Act: -0.0000

Data Index: 591060 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1185. Min Act: -0.0001

Data Index: 1527886 (Python Code)

Max Activating Token Index: 572

Text #14

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1344. Min Act: -0.0001

Data Index: 40761 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1331. Min Act: -0.0001

Data Index: 1563558 (Python Code)

Max Activating Token Index: 546

Text #16

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1388262 (Python Code)

Max Activating Token Index: 814

Text #17

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1450. Min Act: -0.0001

Data Index: 559341 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1323. Min Act: -0.0001

Data Index: 1630729 (Python Code)

Max Activating Token Index: 241

Text #19

Max Range: 0.2657. Min Range: -0.2657

Max Act: 0.1362. Min Act: -0.0001

Data Index: 1622927 (Python Code)

Max Activating Token Index: 599