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

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

Neuron 169 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: 0.8481. Min Range: -0.8481

Max Act: 0.8481. Min Act: -0.0001

Data Index: 677519 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.7975. Min Act: -0.0001

Data Index: 386933 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.7985. Min Act: -0.0001

Data Index: 228897 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.7054. Min Act: -0.0001

Data Index: 771308 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.6643. Min Act: -0.0001

Data Index: 599424 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.6646. Min Act: -0.0001

Data Index: 966790 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.6506. Min Act: -0.0001

Data Index: 91685 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.6035. Min Act: -0.0001

Data Index: 751232 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.6217. Min Act: -0.0001

Data Index: 448842 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.6291. Min Act: -0.0001

Data Index: 1125025 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.6522. Min Act: -0.0001

Data Index: 1269650 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.6019. Min Act: -0.0001

Data Index: 154009 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.7005. Min Act: -0.0001

Data Index: 809307 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5176. Min Act: -0.0001

Data Index: 882147 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5812. Min Act: -0.0001

Data Index: 571559 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5535. Min Act: -0.0001

Data Index: 281110 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5435. Min Act: -0.0001

Data Index: 948725 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.6275. Min Act: -0.0001

Data Index: 854760 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5480. Min Act: -0.0001

Data Index: 985787 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 0.8481. Min Range: -0.8481

Max Act: 0.5734. Min Act: -0.0001

Data Index: 1292554 (C4 (Web Text))

Max Activating Token Index: 572