Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3490 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2357. Min Range: -1.2357

Max Act: 1.2357. Min Act: -0.0000

Data Index: 1481764 (Python Code)

Max Activating Token Index: 937

Text #1

Max Range: 1.2357. Min Range: -1.2357

Max Act: 1.1541. Min Act: -0.0000

Data Index: 1411856 (Python Code)

Max Activating Token Index: 295

Text #2

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.9581. Min Act: -0.0000

Data Index: 1422072 (Python Code)

Max Activating Token Index: 621

Text #3

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.9552. Min Act: -0.0000

Data Index: 1366968 (Python Code)

Max Activating Token Index: 486

Text #4

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1422189 (Python Code)

Max Activating Token Index: 270

Text #5

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.9677. Min Act: -0.0000

Data Index: 1617482 (Python Code)

Max Activating Token Index: 117

Text #6

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.9549. Min Act: -0.0000

Data Index: 1492974 (Python Code)

Max Activating Token Index: 1003

Text #7

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.9302. Min Act: -0.0000

Data Index: 1387552 (Python Code)

Max Activating Token Index: 146

Text #8

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.9328. Min Act: -0.0000

Data Index: 1632590 (Python Code)

Max Activating Token Index: 306

Text #9

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.8151. Min Act: -0.0000

Data Index: 1370033 (Python Code)

Max Activating Token Index: 643

Text #10

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.9027. Min Act: -0.0000

Data Index: 1557953 (Python Code)

Max Activating Token Index: 353

Text #11

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.9064. Min Act: -0.0000

Data Index: 1463762 (Python Code)

Max Activating Token Index: 87

Text #12

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.9419. Min Act: -0.0000

Data Index: 1404957 (Python Code)

Max Activating Token Index: 318

Text #13

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.8870. Min Act: -0.0000

Data Index: 1379470 (Python Code)

Max Activating Token Index: 134

Text #14

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1578413 (Python Code)

Max Activating Token Index: 133

Text #15

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1550138 (Python Code)

Max Activating Token Index: 292

Text #16

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.8365. Min Act: -0.0000

Data Index: 1385081 (Python Code)

Max Activating Token Index: 511

Text #17

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.7880. Min Act: -0.0000

Data Index: 1636079 (Python Code)

Max Activating Token Index: 361

Text #18

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.8631. Min Act: -0.0000

Data Index: 1461149 (Python Code)

Max Activating Token Index: 856

Text #19

Max Range: 1.2357. Min Range: -1.2357

Max Act: 0.8068. Min Act: -0.0000

Data Index: 1627925 (Python Code)

Max Activating Token Index: 487