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

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

Neuron 5608 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.1531. Min Act: -0.0000

Data Index: 1633429 (Python Code)

Max Activating Token Index: 864

Text #1

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.0335. Min Act: -0.0000

Data Index: 576340 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.0479. Min Act: -0.0000

Data Index: 1601458 (Python Code)

Max Activating Token Index: 388

Text #3

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.1089. Min Act: -0.0000

Data Index: 1616268 (Python Code)

Max Activating Token Index: 478

Text #4

Max Range: 1.1531. Min Range: -1.1531

Max Act: 1.0384. Min Act: -0.0000

Data Index: 28297 (C4 (Web Text))

Max Activating Token Index: 389

Text #5

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1579506 (Python Code)

Max Activating Token Index: 297

Text #6

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8716. Min Act: -0.0000

Data Index: 1634252 (Python Code)

Max Activating Token Index: 257

Text #7

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8105. Min Act: -0.0000

Data Index: 1500537 (Python Code)

Max Activating Token Index: 275

Text #8

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7252. Min Act: -0.0000

Data Index: 1460925 (Python Code)

Max Activating Token Index: 879

Text #9

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8887. Min Act: -0.0000

Data Index: 1365366 (Python Code)

Max Activating Token Index: 147

Text #10

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8469. Min Act: -0.0000

Data Index: 1541062 (Python Code)

Max Activating Token Index: 379

Text #11

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.8516. Min Act: -0.0000

Data Index: 1429525 (Python Code)

Max Activating Token Index: 306

Text #12

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7823. Min Act: -0.0000

Data Index: 1199241 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.6641. Min Act: -0.0000

Data Index: 1509929 (Python Code)

Max Activating Token Index: 418

Text #14

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7084. Min Act: -0.0000

Data Index: 564798 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7003. Min Act: -0.0000

Data Index: 1634043 (Python Code)

Max Activating Token Index: 236

Text #16

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1409741 (Python Code)

Max Activating Token Index: 611

Text #17

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7325. Min Act: -0.0000

Data Index: 1551844 (Python Code)

Max Activating Token Index: 1014

Text #18

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.7069. Min Act: -0.0000

Data Index: 1530489 (Python Code)

Max Activating Token Index: 154

Text #19

Max Range: 1.1531. Min Range: -1.1531

Max Act: 0.6617. Min Act: -0.0000

Data Index: 1459856 (Python Code)

Max Activating Token Index: 397