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

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

Neuron 3368 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6505. Min Act: -0.0001

Data Index: 1526656 (Python Code)

Max Activating Token Index: 384

Text #1

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6667. Min Act: -0.0001

Data Index: 1378317 (Python Code)

Max Activating Token Index: 742

Text #2

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.6281. Min Act: -0.0001

Data Index: 1450881 (Python Code)

Max Activating Token Index: 973

Text #3

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.5350. Min Act: -0.0001

Data Index: 1578641 (Python Code)

Max Activating Token Index: 649

Text #4

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.5551. Min Act: -0.0001

Data Index: 1629359 (Python Code)

Max Activating Token Index: 340

Text #5

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.5405. Min Act: -0.0001

Data Index: 1493305 (Python Code)

Max Activating Token Index: 420

Text #6

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.4372. Min Act: -0.0001

Data Index: 1631054 (Python Code)

Max Activating Token Index: 248

Text #7

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.4839. Min Act: -0.0001

Data Index: 1377510 (Python Code)

Max Activating Token Index: 801

Text #8

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.4352. Min Act: -0.0001

Data Index: 1641974 (Python Code)

Max Activating Token Index: 295

Text #9

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.4781. Min Act: -0.0001

Data Index: 1578393 (Python Code)

Max Activating Token Index: 835

Text #10

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.4581. Min Act: -0.0001

Data Index: 1593608 (Python Code)

Max Activating Token Index: 715

Text #11

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.4634. Min Act: -0.0000

Data Index: 1523517 (Python Code)

Max Activating Token Index: 347

Text #12

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.4842. Min Act: -0.0001

Data Index: 1379929 (Python Code)

Max Activating Token Index: 455

Text #13

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.4899. Min Act: -0.0001

Data Index: 1460577 (Python Code)

Max Activating Token Index: 268

Text #14

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.4443. Min Act: -0.0001

Data Index: 1618150 (Python Code)

Max Activating Token Index: 927

Text #15

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.3428. Min Act: -0.0001

Data Index: 1580738 (Python Code)

Max Activating Token Index: 628

Text #16

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.4299. Min Act: -0.0001

Data Index: 1585559 (Python Code)

Max Activating Token Index: 398

Text #17

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.4650. Min Act: -0.0001

Data Index: 1364481 (Python Code)

Max Activating Token Index: 848

Text #18

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.3645. Min Act: -0.0001

Data Index: 1634659 (Python Code)

Max Activating Token Index: 157

Text #19

Max Range: 1.6667. Min Range: -1.6667

Max Act: 1.3984. Min Act: -0.0001

Data Index: 1548768 (Python Code)

Max Activating Token Index: 310