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

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

Neuron 1680 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3574. Min Act: -0.0001

Data Index: 1518212 (Python Code)

Max Activating Token Index: 83

Text #1

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2955. Min Act: 0.0000

Data Index: 1471589 (Python Code)

Max Activating Token Index: 258

Text #2

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2541. Min Act: -0.0000

Data Index: 1627037 (Python Code)

Max Activating Token Index: 77

Text #3

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2563. Min Act: 0.0000

Data Index: 1591458 (Python Code)

Max Activating Token Index: 966

Text #4

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2476. Min Act: -0.0000

Data Index: 1380112 (Python Code)

Max Activating Token Index: 252

Text #5

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2537. Min Act: 0.0001

Data Index: 1414505 (Python Code)

Max Activating Token Index: 733

Text #6

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2438. Min Act: -0.0001

Data Index: 1635309 (Python Code)

Max Activating Token Index: 759

Text #7

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1515874 (Python Code)

Max Activating Token Index: 647

Text #8

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1638123 (Python Code)

Max Activating Token Index: 595

Text #9

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2345. Min Act: 0.0000

Data Index: 1549588 (Python Code)

Max Activating Token Index: 932

Text #10

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1458390 (Python Code)

Max Activating Token Index: 341

Text #11

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2279. Min Act: -0.0001

Data Index: 1411718 (Python Code)

Max Activating Token Index: 494

Text #12

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1406494 (Python Code)

Max Activating Token Index: 320

Text #13

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2256. Min Act: -0.0000

Data Index: 1565944 (Python Code)

Max Activating Token Index: 128

Text #14

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1520441 (Python Code)

Max Activating Token Index: 164

Text #15

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2409. Min Act: 0.0000

Data Index: 1637833 (Python Code)

Max Activating Token Index: 887

Text #16

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1364825 (Python Code)

Max Activating Token Index: 628

Text #17

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1460305 (Python Code)

Max Activating Token Index: 865

Text #18

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2190. Min Act: 0.0000

Data Index: 1447764 (Python Code)

Max Activating Token Index: 830

Text #19

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1415934 (Python Code)

Max Activating Token Index: 405