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

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

Neuron 3257 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.5820. Min Act: -0.0000

Data Index: 1335350 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.3615. Min Act: -0.0000

Data Index: 392461 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.3353. Min Act: -0.0000

Data Index: 562119 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.3209. Min Act: -0.0000

Data Index: 1571406 (Python Code)

Max Activating Token Index: 663

Text #4

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.2775. Min Act: -0.0000

Data Index: 299732 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.2054. Min Act: -0.0000

Data Index: 1565320 (Python Code)

Max Activating Token Index: 223

Text #6

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.2142. Min Act: -0.0000

Data Index: 1409177 (Python Code)

Max Activating Token Index: 844

Text #7

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.1369. Min Act: -0.0000

Data Index: 1599050 (Python Code)

Max Activating Token Index: 197

Text #8

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.2112. Min Act: -0.0000

Data Index: 1378391 (Python Code)

Max Activating Token Index: 435

Text #9

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.1668. Min Act: -0.0000

Data Index: 103326 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.2416. Min Act: -0.0000

Data Index: 1578711 (Python Code)

Max Activating Token Index: 144

Text #11

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.1647. Min Act: -0.0000

Data Index: 1534128 (Python Code)

Max Activating Token Index: 131

Text #12

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.1146. Min Act: -0.0000

Data Index: 1612602 (Python Code)

Max Activating Token Index: 862

Text #13

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.1160. Min Act: -0.0000

Data Index: 1590222 (Python Code)

Max Activating Token Index: 988

Text #14

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.1532. Min Act: -0.0000

Data Index: 1601896 (Python Code)

Max Activating Token Index: 113

Text #15

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.0772. Min Act: -0.0000

Data Index: 1646372 (Python Code)

Max Activating Token Index: 376

Text #16

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.1533. Min Act: -0.0000

Data Index: 1539900 (Python Code)

Max Activating Token Index: 302

Text #17

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.1053. Min Act: -0.0000

Data Index: 1062675 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.0481. Min Act: -0.0000

Data Index: 1625735 (Python Code)

Max Activating Token Index: 945

Text #19

Max Range: 1.5820. Min Range: -1.5820

Max Act: 1.0850. Min Act: -0.0000

Data Index: 1461420 (Python Code)

Max Activating Token Index: 38