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

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

Neuron 1070 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.9234. Min Act: -0.0000

Data Index: 1158175 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.9562. Min Act: -0.0000

Data Index: 342466 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.8846. Min Act: -0.0000

Data Index: 698711 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.9082. Min Act: -0.0000

Data Index: 1335166 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.8212. Min Act: -0.0000

Data Index: 365759 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.7553. Min Act: -0.0000

Data Index: 881778 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.7855. Min Act: -0.0000

Data Index: 1273140 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.7276. Min Act: -0.0000

Data Index: 413904 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.7640. Min Act: -0.0000

Data Index: 633551 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1003830 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.7871. Min Act: -0.0000

Data Index: 969943 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.7218. Min Act: -0.0000

Data Index: 713718 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.7388. Min Act: -0.0000

Data Index: 120900 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.7275. Min Act: -0.0000

Data Index: 26388 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.7182. Min Act: -0.0000

Data Index: 1177426 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.6658. Min Act: -0.0000

Data Index: 862898 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1226949 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.7077. Min Act: -0.0000

Data Index: 540134 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.6377. Min Act: -0.0000

Data Index: 517127 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.9562. Min Range: -0.9562

Max Act: 0.6973. Min Act: -0.0000

Data Index: 956930 (C4 (Web Text))

Max Activating Token Index: 89