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

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

Neuron 144 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.8448. Min Act: -0.0000

Data Index: 1478531 (Python Code)

Max Activating Token Index: 654

Text #1

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1607816 (Python Code)

Max Activating Token Index: 734

Text #2

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1643830 (Python Code)

Max Activating Token Index: 202

Text #3

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1376593 (Python Code)

Max Activating Token Index: 346

Text #4

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1438310 (Python Code)

Max Activating Token Index: 938

Text #5

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1489316 (Python Code)

Max Activating Token Index: 811

Text #6

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1464057 (Python Code)

Max Activating Token Index: 549

Text #7

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.4372. Min Act: -0.0000

Data Index: 1424561 (Python Code)

Max Activating Token Index: 384

Text #8

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.4485. Min Act: -0.0000

Data Index: 1392686 (Python Code)

Max Activating Token Index: 138

Text #9

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.4625. Min Act: -0.0000

Data Index: 1407879 (Python Code)

Max Activating Token Index: 533

Text #10

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.4552. Min Act: -0.0000

Data Index: 1572060 (Python Code)

Max Activating Token Index: 91

Text #11

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1476525 (Python Code)

Max Activating Token Index: 918

Text #12

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1466174 (Python Code)

Max Activating Token Index: 312

Text #13

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1381616 (Python Code)

Max Activating Token Index: 631

Text #14

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.4376. Min Act: -0.0000

Data Index: 1516270 (Python Code)

Max Activating Token Index: 536

Text #15

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1647797 (Python Code)

Max Activating Token Index: 531

Text #16

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.4328. Min Act: -0.0000

Data Index: 1399961 (Python Code)

Max Activating Token Index: 371

Text #17

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.4058. Min Act: -0.0000

Data Index: 1402217 (Python Code)

Max Activating Token Index: 1015

Text #18

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.4141. Min Act: -0.0000

Data Index: 1537485 (Python Code)

Max Activating Token Index: 506

Text #19

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1613276 (Python Code)

Max Activating Token Index: 465