Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5333 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1710. Min Act: -0.0000

Data Index: 372090 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1626. Min Act: -0.0000

Data Index: 313267 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1201378 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1428. Min Act: -0.0000

Data Index: 351596 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1415. Min Act: -0.0000

Data Index: 1142951 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1425. Min Act: -0.0000

Data Index: 445664 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1625. Min Act: -0.0000

Data Index: 947322 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1623. Min Act: -0.0000

Data Index: 956443 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1303282 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1786. Min Act: -0.0000

Data Index: 956878 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1628. Min Act: -0.0000

Data Index: 990741 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1311. Min Act: -0.0001

Data Index: 78629 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1435. Min Act: -0.0000

Data Index: 575293 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1600. Min Act: -0.0000

Data Index: 1173674 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1383. Min Act: -0.0001

Data Index: 1275979 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1438. Min Act: -0.0001

Data Index: 638335 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1399. Min Act: -0.0000

Data Index: 372156 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1395. Min Act: -0.0000

Data Index: 797130 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1472. Min Act: -0.0000

Data Index: 416029 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.1786. Min Range: -0.1786

Max Act: 0.1274. Min Act: -0.0000

Data Index: 1287726 (C4 (Web Text))

Max Activating Token Index: 98