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

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

Neuron 5197 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8263. Min Range: -4.8263

Max Act: 4.8263. Min Act: -0.0000

Data Index: 1599799 (Python Code)

Max Activating Token Index: 570

Text #1

Max Range: 4.8263. Min Range: -4.8263

Max Act: 4.3375. Min Act: -0.0000

Data Index: 1645688 (Python Code)

Max Activating Token Index: 148

Text #2

Max Range: 4.8263. Min Range: -4.8263

Max Act: 4.1277. Min Act: -0.0000

Data Index: 1367735 (Python Code)

Max Activating Token Index: 430

Text #3

Max Range: 4.8263. Min Range: -4.8263

Max Act: 3.9040. Min Act: -0.0000

Data Index: 1555610 (Python Code)

Max Activating Token Index: 48

Text #4

Max Range: 4.8263. Min Range: -4.8263

Max Act: 3.6310. Min Act: -0.0000

Data Index: 1493245 (Python Code)

Max Activating Token Index: 826

Text #5

Max Range: 4.8263. Min Range: -4.8263

Max Act: 3.5241. Min Act: -0.0000

Data Index: 1638241 (Python Code)

Max Activating Token Index: 161

Text #6

Max Range: 4.8263. Min Range: -4.8263

Max Act: 3.2440. Min Act: -0.0000

Data Index: 1586124 (Python Code)

Max Activating Token Index: 441

Text #7

Max Range: 4.8263. Min Range: -4.8263

Max Act: 3.3412. Min Act: -0.0000

Data Index: 1635848 (Python Code)

Max Activating Token Index: 238

Text #8

Max Range: 4.8263. Min Range: -4.8263

Max Act: 3.3514. Min Act: -0.0000

Data Index: 1611025 (Python Code)

Max Activating Token Index: 154

Text #9

Max Range: 4.8263. Min Range: -4.8263

Max Act: 3.4881. Min Act: -0.0000

Data Index: 1640219 (Python Code)

Max Activating Token Index: 386

Text #10

Max Range: 4.8263. Min Range: -4.8263

Max Act: 3.2595. Min Act: -0.0000

Data Index: 1618747 (Python Code)

Max Activating Token Index: 618

Text #11

Max Range: 4.8263. Min Range: -4.8263

Max Act: 3.1987. Min Act: -0.0000

Data Index: 1578906 (Python Code)

Max Activating Token Index: 148

Text #12

Max Range: 4.8263. Min Range: -4.8263

Max Act: 3.0180. Min Act: -0.0000

Data Index: 1404950 (Python Code)

Max Activating Token Index: 88

Text #13

Max Range: 4.8263. Min Range: -4.8263

Max Act: 2.9915. Min Act: -0.0000

Data Index: 1460695 (Python Code)

Max Activating Token Index: 213

Text #14

Max Range: 4.8263. Min Range: -4.8263

Max Act: 3.1090. Min Act: -0.0000

Data Index: 1631004 (Python Code)

Max Activating Token Index: 434

Text #15

Max Range: 4.8263. Min Range: -4.8263

Max Act: 3.1193. Min Act: -0.0000

Data Index: 1433516 (Python Code)

Max Activating Token Index: 214

Text #16

Max Range: 4.8263. Min Range: -4.8263

Max Act: 3.0575. Min Act: -0.0000

Data Index: 1540512 (Python Code)

Max Activating Token Index: 144

Text #17

Max Range: 4.8263. Min Range: -4.8263

Max Act: 3.1903. Min Act: -0.0000

Data Index: 1403081 (Python Code)

Max Activating Token Index: 721

Text #18

Max Range: 4.8263. Min Range: -4.8263

Max Act: 3.0243. Min Act: -0.0000

Data Index: 1481290 (Python Code)

Max Activating Token Index: 112

Text #19

Max Range: 4.8263. Min Range: -4.8263

Max Act: 3.0040. Min Act: -0.0000

Data Index: 1633813 (Python Code)

Max Activating Token Index: 228