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

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

Neuron 1320 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6492. Min Range: -3.6492

Max Act: 3.5771. Min Act: -0.0000

Data Index: 1360603 (Python Code)

Max Activating Token Index: 281

Text #1

Max Range: 3.6492. Min Range: -3.6492

Max Act: 3.6492. Min Act: -0.0000

Data Index: 1423910 (Python Code)

Max Activating Token Index: 960

Text #2

Max Range: 3.6492. Min Range: -3.6492

Max Act: 3.3472. Min Act: -0.0000

Data Index: 1399171 (Python Code)

Max Activating Token Index: 777

Text #3

Max Range: 3.6492. Min Range: -3.6492

Max Act: 3.1923. Min Act: -0.0000

Data Index: 1536320 (Python Code)

Max Activating Token Index: 1009

Text #4

Max Range: 3.6492. Min Range: -3.6492

Max Act: 3.2975. Min Act: -0.0000

Data Index: 1566209 (Python Code)

Max Activating Token Index: 114

Text #5

Max Range: 3.6492. Min Range: -3.6492

Max Act: 3.4332. Min Act: -0.0000

Data Index: 1649196 (Python Code)

Max Activating Token Index: 263

Text #6

Max Range: 3.6492. Min Range: -3.6492

Max Act: 3.2314. Min Act: -0.0000

Data Index: 1652822 (Python Code)

Max Activating Token Index: 951

Text #7

Max Range: 3.6492. Min Range: -3.6492

Max Act: 3.1341. Min Act: -0.0000

Data Index: 1469680 (Python Code)

Max Activating Token Index: 321

Text #8

Max Range: 3.6492. Min Range: -3.6492

Max Act: 3.4485. Min Act: -0.0000

Data Index: 1368380 (Python Code)

Max Activating Token Index: 738

Text #9

Max Range: 3.6492. Min Range: -3.6492

Max Act: 2.8918. Min Act: -0.0000

Data Index: 1430032 (Python Code)

Max Activating Token Index: 175

Text #10

Max Range: 3.6492. Min Range: -3.6492

Max Act: 3.1495. Min Act: -0.0000

Data Index: 1392123 (Python Code)

Max Activating Token Index: 731

Text #11

Max Range: 3.6492. Min Range: -3.6492

Max Act: 3.0708. Min Act: -0.0000

Data Index: 1499267 (Python Code)

Max Activating Token Index: 931

Text #12

Max Range: 3.6492. Min Range: -3.6492

Max Act: 2.9198. Min Act: -0.0000

Data Index: 1450761 (Python Code)

Max Activating Token Index: 1022

Text #13

Max Range: 3.6492. Min Range: -3.6492

Max Act: 2.8999. Min Act: -0.0000

Data Index: 1543338 (Python Code)

Max Activating Token Index: 778

Text #14

Max Range: 3.6492. Min Range: -3.6492

Max Act: 3.0096. Min Act: -0.0000

Data Index: 1533537 (Python Code)

Max Activating Token Index: 732

Text #15

Max Range: 3.6492. Min Range: -3.6492

Max Act: 2.9684. Min Act: -0.0000

Data Index: 1630572 (Python Code)

Max Activating Token Index: 809

Text #16

Max Range: 3.6492. Min Range: -3.6492

Max Act: 2.8304. Min Act: -0.0000

Data Index: 1397862 (Python Code)

Max Activating Token Index: 294

Text #17

Max Range: 3.6492. Min Range: -3.6492

Max Act: 2.9763. Min Act: -0.0000

Data Index: 1402580 (Python Code)

Max Activating Token Index: 917

Text #18

Max Range: 3.6492. Min Range: -3.6492

Max Act: 2.9567. Min Act: -0.0000

Data Index: 1418352 (Python Code)

Max Activating Token Index: 408

Text #19

Max Range: 3.6492. Min Range: -3.6492

Max Act: 2.9284. Min Act: -0.0000

Data Index: 1621069 (Python Code)

Max Activating Token Index: 25