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

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

Neuron 576 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2378. Min Act: -0.0001

Data Index: 183367 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2423. Min Act: -0.0001

Data Index: 29540 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2396. Min Act: -0.0000

Data Index: 10607 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2407. Min Act: -0.0000

Data Index: 1090741 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2283. Min Act: -0.0001

Data Index: 655503 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2081. Min Act: -0.0000

Data Index: 492985 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2036. Min Act: -0.0000

Data Index: 72642 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1309117 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1021590 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.1900. Min Act: -0.0000

Data Index: 1007269 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2099. Min Act: -0.0001

Data Index: 548134 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.1976. Min Act: -0.0000

Data Index: 1021974 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2058. Min Act: -0.0000

Data Index: 29303 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.1756. Min Act: -0.0001

Data Index: 1220398 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.1929. Min Act: -0.0000

Data Index: 280219 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.1795. Min Act: -0.0001

Data Index: 657176 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.2005. Min Act: -0.0000

Data Index: 631190 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.1859. Min Act: -0.0000

Data Index: 506029 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.1756. Min Act: -0.0001

Data Index: 77712 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 0.2423. Min Range: -0.2423

Max Act: 0.1835. Min Act: -0.0000

Data Index: 468845 (C4 (Web Text))

Max Activating Token Index: 52