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

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

Neuron 5110 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2705. Min Act: -0.0001

Data Index: 563139 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2452. Min Act: -0.0001

Data Index: 359207 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2377. Min Act: -0.0001

Data Index: 623386 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2171. Min Act: -0.0001

Data Index: 418041 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2357. Min Act: -0.0001

Data Index: 27802 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2080. Min Act: -0.0001

Data Index: 1529893 (Python Code)

Max Activating Token Index: 891

Text #6

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2117. Min Act: -0.0001

Data Index: 991622 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1881. Min Act: -0.0001

Data Index: 520359 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2282. Min Act: -0.0001

Data Index: 336406 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1902. Min Act: -0.0001

Data Index: 490899 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2078. Min Act: -0.0001

Data Index: 501083 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1871. Min Act: -0.0001

Data Index: 1423129 (Python Code)

Max Activating Token Index: 249

Text #12

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.2029. Min Act: -0.0001

Data Index: 1148702 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1970. Min Act: -0.0001

Data Index: 218149 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1773. Min Act: -0.0001

Data Index: 875760 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1967. Min Act: -0.0001

Data Index: 523291 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1822. Min Act: -0.0001

Data Index: 1053111 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1708. Min Act: -0.0001

Data Index: 280342 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1883. Min Act: -0.0001

Data Index: 1027090 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 0.2705. Min Range: -0.2705

Max Act: 0.1765. Min Act: -0.0001

Data Index: 462992 (C4 (Web Text))

Max Activating Token Index: 448