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

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

Neuron 3359 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.4759. Min Act: -0.0000

Data Index: 1382312 (Python Code)

Max Activating Token Index: 226

Text #1

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.3790. Min Act: -0.0000

Data Index: 1616499 (Python Code)

Max Activating Token Index: 193

Text #2

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.3112. Min Act: -0.0000

Data Index: 1577565 (Python Code)

Max Activating Token Index: 162

Text #3

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.2888. Min Act: -0.0000

Data Index: 1542515 (Python Code)

Max Activating Token Index: 717

Text #4

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.3573. Min Act: -0.0000

Data Index: 369543 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.3310. Min Act: -0.0000

Data Index: 1467301 (Python Code)

Max Activating Token Index: 545

Text #6

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.2147. Min Act: -0.0000

Data Index: 1518263 (Python Code)

Max Activating Token Index: 138

Text #7

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.1343. Min Act: -0.0000

Data Index: 1531649 (Python Code)

Max Activating Token Index: 357

Text #8

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.1663. Min Act: -0.0000

Data Index: 1470646 (Python Code)

Max Activating Token Index: 202

Text #9

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.2323. Min Act: -0.0000

Data Index: 1380545 (Python Code)

Max Activating Token Index: 857

Text #10

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.0897. Min Act: -0.0000

Data Index: 1501431 (Python Code)

Max Activating Token Index: 120

Text #11

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.0840. Min Act: -0.0000

Data Index: 1645780 (Python Code)

Max Activating Token Index: 441

Text #12

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.2047. Min Act: -0.0000

Data Index: 1489842 (Python Code)

Max Activating Token Index: 286

Text #13

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.0514. Min Act: 0.0000

Data Index: 1651878 (Python Code)

Max Activating Token Index: 926

Text #14

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.0652. Min Act: -0.0000

Data Index: 1376421 (Python Code)

Max Activating Token Index: 381

Text #15

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.1593. Min Act: -0.0000

Data Index: 1540148 (Python Code)

Max Activating Token Index: 558

Text #16

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.0581. Min Act: -0.0000

Data Index: 1595795 (Python Code)

Max Activating Token Index: 488

Text #17

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1506546 (Python Code)

Max Activating Token Index: 620

Text #18

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.2251. Min Act: -0.0000

Data Index: 1631442 (Python Code)

Max Activating Token Index: 319

Text #19

Max Range: 1.4759. Min Range: -1.4759

Max Act: 1.0141. Min Act: -0.0000

Data Index: 1509157 (Python Code)

Max Activating Token Index: 124