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

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

Neuron 2864 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.8575. Min Act: -0.0001

Data Index: 1412549 (Python Code)

Max Activating Token Index: 842

Text #1

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.8267. Min Act: -0.0000

Data Index: 1648322 (Python Code)

Max Activating Token Index: 254

Text #2

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.7968. Min Act: -0.0000

Data Index: 1602086 (Python Code)

Max Activating Token Index: 718

Text #3

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.7530. Min Act: -0.0000

Data Index: 1598123 (Python Code)

Max Activating Token Index: 496

Text #4

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.7106. Min Act: -0.0000

Data Index: 1447443 (Python Code)

Max Activating Token Index: 339

Text #5

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.7204. Min Act: -0.0001

Data Index: 1653728 (Python Code)

Max Activating Token Index: 408

Text #6

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1476663 (Python Code)

Max Activating Token Index: 718

Text #7

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.7018. Min Act: -0.0000

Data Index: 1481114 (Python Code)

Max Activating Token Index: 446

Text #8

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1521195 (Python Code)

Max Activating Token Index: 983

Text #9

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1412441 (Python Code)

Max Activating Token Index: 521

Text #10

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.6640. Min Act: -0.0001

Data Index: 1588271 (Python Code)

Max Activating Token Index: 212

Text #11

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.6634. Min Act: -0.0000

Data Index: 1509687 (Python Code)

Max Activating Token Index: 925

Text #12

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.6406. Min Act: -0.0000

Data Index: 1622251 (Python Code)

Max Activating Token Index: 415

Text #13

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.6591. Min Act: -0.0001

Data Index: 1600469 (Python Code)

Max Activating Token Index: 228

Text #14

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.6547. Min Act: -0.0000

Data Index: 1399067 (Python Code)

Max Activating Token Index: 308

Text #15

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.6511. Min Act: -0.0000

Data Index: 1440445 (Python Code)

Max Activating Token Index: 883

Text #16

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.6328. Min Act: -0.0000

Data Index: 1584416 (Python Code)

Max Activating Token Index: 524

Text #17

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.6475. Min Act: -0.0001

Data Index: 1388946 (Python Code)

Max Activating Token Index: 265

Text #18

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.6605. Min Act: -0.0001

Data Index: 1382329 (Python Code)

Max Activating Token Index: 963

Text #19

Max Range: 0.8575. Min Range: -0.8575

Max Act: 0.6176. Min Act: -0.0001

Data Index: 1393210 (Python Code)

Max Activating Token Index: 256