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

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

Neuron 4083 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: 0.1711. Min Range: -0.1711

Max Act: 0.1586. Min Act: -0.0001

Data Index: 510863 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1566. Min Act: -0.0000

Data Index: 432574 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1711. Min Act: -0.0001

Data Index: 1007455 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1592. Min Act: -0.0001

Data Index: 355349 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1527. Min Act: -0.0001

Data Index: 593400 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1491. Min Act: -0.0000

Data Index: 503562 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1351. Min Act: -0.0001

Data Index: 365821 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1482. Min Act: -0.0001

Data Index: 228239 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1470. Min Act: -0.0001

Data Index: 123601 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1486. Min Act: -0.0000

Data Index: 75530 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1410. Min Act: -0.0001

Data Index: 1093233 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1442. Min Act: -0.0000

Data Index: 407589 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1317. Min Act: -0.0001

Data Index: 593882 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1269. Min Act: -0.0000

Data Index: 526808 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1392. Min Act: -0.0000

Data Index: 524210 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1394. Min Act: -0.0001

Data Index: 1075180 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1342. Min Act: -0.0000

Data Index: 513552 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1323. Min Act: -0.0000

Data Index: 34281 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1272. Min Act: -0.0001

Data Index: 881642 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1349. Min Act: -0.0001

Data Index: 1235911 (C4 (Web Text))

Max Activating Token Index: 473