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

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

Neuron 981 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: 0.7039. Min Range: -0.7039

Max Act: 0.6633. Min Act: -0.0000

Data Index: 787473 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1509469 (Python Code)

Max Activating Token Index: 69

Text #2

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.6535. Min Act: -0.0000

Data Index: 809256 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.6596. Min Act: -0.0000

Data Index: 1566213 (Python Code)

Max Activating Token Index: 156

Text #4

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1478688 (Python Code)

Max Activating Token Index: 214

Text #5

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.6682. Min Act: -0.0000

Data Index: 85421 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.5919. Min Act: -0.0000

Data Index: 1543350 (Python Code)

Max Activating Token Index: 296

Text #7

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1408461 (Python Code)

Max Activating Token Index: 695

Text #8

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.6887. Min Act: -0.0000

Data Index: 1405633 (Python Code)

Max Activating Token Index: 852

Text #9

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1588690 (Python Code)

Max Activating Token Index: 137

Text #10

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.4860. Min Act: -0.0000

Data Index: 345493 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1547061 (Python Code)

Max Activating Token Index: 842

Text #12

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.4294. Min Act: -0.0000

Data Index: 704168 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.4750. Min Act: -0.0000

Data Index: 1631069 (Python Code)

Max Activating Token Index: 167

Text #14

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.4157. Min Act: -0.0000

Data Index: 19061 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1117350 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1540981 (Python Code)

Max Activating Token Index: 896

Text #17

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.3700. Min Act: -0.0000

Data Index: 91831 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.4154. Min Act: -0.0000

Data Index: 1477374 (Python Code)

Max Activating Token Index: 122

Text #19

Max Range: 0.7039. Min Range: -0.7039

Max Act: 0.3990. Min Act: -0.0000

Data Index: 464177 (C4 (Web Text))

Max Activating Token Index: 163