Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 15 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.6159. Min Act: -0.0003

Data Index: 1520579 (Python Code)

Max Activating Token Index: 45

Text #1

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.5991. Min Act: -0.0003

Data Index: 1409992 (Python Code)

Max Activating Token Index: 196

Text #2

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.5129. Min Act: -0.0003

Data Index: 1407850 (Python Code)

Max Activating Token Index: 638

Text #3

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.5213. Min Act: -0.0003

Data Index: 1441028 (Python Code)

Max Activating Token Index: 610

Text #4

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4659. Min Act: -0.0003

Data Index: 1500853 (Python Code)

Max Activating Token Index: 919

Text #5

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4930. Min Act: -0.0003

Data Index: 1480389 (Python Code)

Max Activating Token Index: 575

Text #6

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4707. Min Act: -0.0003

Data Index: 1517457 (Python Code)

Max Activating Token Index: 710

Text #7

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4547. Min Act: -0.0003

Data Index: 1402825 (Python Code)

Max Activating Token Index: 32

Text #8

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4704. Min Act: -0.0003

Data Index: 1576782 (Python Code)

Max Activating Token Index: 457

Text #9

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4440. Min Act: -0.0003

Data Index: 1579163 (Python Code)

Max Activating Token Index: 723

Text #10

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4443. Min Act: -0.0003

Data Index: 1489991 (Python Code)

Max Activating Token Index: 785

Text #11

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4582. Min Act: -0.0003

Data Index: 1377617 (Python Code)

Max Activating Token Index: 298

Text #12

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4549. Min Act: -0.0003

Data Index: 504518 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4694. Min Act: -0.0003

Data Index: 1443386 (Python Code)

Max Activating Token Index: 60

Text #14

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4639. Min Act: -0.0003

Data Index: 1383803 (Python Code)

Max Activating Token Index: 319

Text #15

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4460. Min Act: -0.0003

Data Index: 1427327 (Python Code)

Max Activating Token Index: 667

Text #16

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4026. Min Act: -0.0003

Data Index: 1479833 (Python Code)

Max Activating Token Index: 645

Text #17

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4442. Min Act: -0.0003

Data Index: 1450550 (Python Code)

Max Activating Token Index: 739

Text #18

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4423. Min Act: -0.0003

Data Index: 1363443 (Python Code)

Max Activating Token Index: 373

Text #19

Max Range: 0.6159. Min Range: -0.6159

Max Act: 0.4429. Min Act: -0.0003

Data Index: 1605075 (Python Code)

Max Activating Token Index: 452