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

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

Neuron 51 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: 2.5161. Min Range: -2.5161

Max Act: 2.4337. Min Act: -0.0000

Data Index: 1645922 (Python Code)

Max Activating Token Index: 412

Text #1

Max Range: 2.5161. Min Range: -2.5161

Max Act: 2.5161. Min Act: -0.0000

Data Index: 1388245 (Python Code)

Max Activating Token Index: 570

Text #2

Max Range: 2.5161. Min Range: -2.5161

Max Act: 2.4828. Min Act: -0.0000

Data Index: 1367657 (Python Code)

Max Activating Token Index: 661

Text #3

Max Range: 2.5161. Min Range: -2.5161

Max Act: 2.1456. Min Act: -0.0000

Data Index: 1384997 (Python Code)

Max Activating Token Index: 814

Text #4

Max Range: 2.5161. Min Range: -2.5161

Max Act: 2.4229. Min Act: -0.0000

Data Index: 1372153 (Python Code)

Max Activating Token Index: 405

Text #5

Max Range: 2.5161. Min Range: -2.5161

Max Act: 2.1675. Min Act: -0.0000

Data Index: 1490806 (Python Code)

Max Activating Token Index: 617

Text #6

Max Range: 2.5161. Min Range: -2.5161

Max Act: 2.2708. Min Act: -0.0000

Data Index: 1402431 (Python Code)

Max Activating Token Index: 396

Text #7

Max Range: 2.5161. Min Range: -2.5161

Max Act: 1.8805. Min Act: -0.0000

Data Index: 1476392 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 2.5161. Min Range: -2.5161

Max Act: 2.3132. Min Act: -0.0000

Data Index: 1498515 (Python Code)

Max Activating Token Index: 437

Text #9

Max Range: 2.5161. Min Range: -2.5161

Max Act: 2.1524. Min Act: -0.0000

Data Index: 1594900 (Python Code)

Max Activating Token Index: 659

Text #10

Max Range: 2.5161. Min Range: -2.5161

Max Act: 2.1506. Min Act: -0.0000

Data Index: 1570765 (Python Code)

Max Activating Token Index: 585

Text #11

Max Range: 2.5161. Min Range: -2.5161

Max Act: 1.8754. Min Act: -0.0000

Data Index: 1429252 (Python Code)

Max Activating Token Index: 309

Text #12

Max Range: 2.5161. Min Range: -2.5161

Max Act: 2.0805. Min Act: -0.0000

Data Index: 1637424 (Python Code)

Max Activating Token Index: 627

Text #13

Max Range: 2.5161. Min Range: -2.5161

Max Act: 1.9499. Min Act: -0.0000

Data Index: 1548970 (Python Code)

Max Activating Token Index: 106

Text #14

Max Range: 2.5161. Min Range: -2.5161

Max Act: 1.9571. Min Act: -0.0000

Data Index: 1451455 (Python Code)

Max Activating Token Index: 527

Text #15

Max Range: 2.5161. Min Range: -2.5161

Max Act: 2.0024. Min Act: -0.0000

Data Index: 1621279 (Python Code)

Max Activating Token Index: 867

Text #16

Max Range: 2.5161. Min Range: -2.5161

Max Act: 1.8997. Min Act: -0.0000

Data Index: 1461230 (Python Code)

Max Activating Token Index: 81

Text #17

Max Range: 2.5161. Min Range: -2.5161

Max Act: 2.0828. Min Act: -0.0000

Data Index: 1571176 (Python Code)

Max Activating Token Index: 872

Text #18

Max Range: 2.5161. Min Range: -2.5161

Max Act: 1.7777. Min Act: -0.0000

Data Index: 1579003 (Python Code)

Max Activating Token Index: 827

Text #19

Max Range: 2.5161. Min Range: -2.5161

Max Act: 1.8716. Min Act: -0.0000

Data Index: 1498607 (Python Code)

Max Activating Token Index: 108