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

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

Neuron 3119 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0763. Min Range: -2.0763

Max Act: 2.0763. Min Act: -0.0000

Data Index: 1441385 (Python Code)

Max Activating Token Index: 98

Text #1

Max Range: 2.0763. Min Range: -2.0763

Max Act: 1.9677. Min Act: -0.0000

Data Index: 1594114 (Python Code)

Max Activating Token Index: 106

Text #2

Max Range: 2.0763. Min Range: -2.0763

Max Act: 1.9056. Min Act: -0.0000

Data Index: 1511238 (Python Code)

Max Activating Token Index: 452

Text #3

Max Range: 2.0763. Min Range: -2.0763

Max Act: 1.9961. Min Act: -0.0000

Data Index: 1496710 (Python Code)

Max Activating Token Index: 436

Text #4

Max Range: 2.0763. Min Range: -2.0763

Max Act: 1.9398. Min Act: -0.0000

Data Index: 1368797 (Python Code)

Max Activating Token Index: 497

Text #5

Max Range: 2.0763. Min Range: -2.0763

Max Act: 1.9571. Min Act: -0.0001

Data Index: 1558666 (Python Code)

Max Activating Token Index: 913

Text #6

Max Range: 2.0763. Min Range: -2.0763

Max Act: 1.8987. Min Act: -0.0000

Data Index: 1595031 (Python Code)

Max Activating Token Index: 381

Text #7

Max Range: 2.0763. Min Range: -2.0763

Max Act: 2.0235. Min Act: -0.0000

Data Index: 1571648 (Python Code)

Max Activating Token Index: 516

Text #8

Max Range: 2.0763. Min Range: -2.0763

Max Act: 1.8879. Min Act: -0.0000

Data Index: 1581348 (Python Code)

Max Activating Token Index: 591

Text #9

Max Range: 2.0763. Min Range: -2.0763

Max Act: 1.8115. Min Act: -0.0000

Data Index: 1499800 (Python Code)

Max Activating Token Index: 505

Text #10

Max Range: 2.0763. Min Range: -2.0763

Max Act: 1.8573. Min Act: -0.0000

Data Index: 1392116 (Python Code)

Max Activating Token Index: 444

Text #11

Max Range: 2.0763. Min Range: -2.0763

Max Act: 1.7885. Min Act: -0.0000

Data Index: 1579406 (Python Code)

Max Activating Token Index: 442

Text #12

Max Range: 2.0763. Min Range: -2.0763

Max Act: 1.8015. Min Act: -0.0000

Data Index: 1651260 (Python Code)

Max Activating Token Index: 992

Text #13

Max Range: 2.0763. Min Range: -2.0763

Max Act: 1.8366. Min Act: -0.0000

Data Index: 1567788 (Python Code)

Max Activating Token Index: 77

Text #14

Max Range: 2.0763. Min Range: -2.0763

Max Act: 1.8920. Min Act: -0.0000

Data Index: 1577259 (Python Code)

Max Activating Token Index: 544

Text #15

Max Range: 2.0763. Min Range: -2.0763

Max Act: 1.8189. Min Act: -0.0000

Data Index: 1395427 (Python Code)

Max Activating Token Index: 459

Text #16

Max Range: 2.0763. Min Range: -2.0763

Max Act: 1.8199. Min Act: -0.0000

Data Index: 1611821 (Python Code)

Max Activating Token Index: 207

Text #17

Max Range: 2.0763. Min Range: -2.0763

Max Act: 1.7594. Min Act: -0.0000

Data Index: 1557953 (Python Code)

Max Activating Token Index: 350

Text #18

Max Range: 2.0763. Min Range: -2.0763

Max Act: 1.7300. Min Act: -0.0000

Data Index: 1524293 (Python Code)

Max Activating Token Index: 582

Text #19

Max Range: 2.0763. Min Range: -2.0763

Max Act: 1.8387. Min Act: -0.0000

Data Index: 1582051 (Python Code)

Max Activating Token Index: 265