Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 242 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.4525. Min Act: -0.0001

Data Index: 208334 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.4135. Min Act: -0.0001

Data Index: 860291 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.4163. Min Act: -0.0002

Data Index: 941217 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.4146. Min Act: -0.0002

Data Index: 48363 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3681. Min Act: -0.0002

Data Index: 125287 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3798. Min Act: -0.0001

Data Index: 373410 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3868. Min Act: -0.0002

Data Index: 664630 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3582. Min Act: -0.0002

Data Index: 1262919 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3534. Min Act: -0.0002

Data Index: 572330 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3266. Min Act: -0.0002

Data Index: 1049731 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3350. Min Act: -0.0001

Data Index: 1043968 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3193. Min Act: -0.0002

Data Index: 307462 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3440. Min Act: -0.0002

Data Index: 1100982 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3274. Min Act: -0.0001

Data Index: 590015 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3151. Min Act: -0.0001

Data Index: 1241429 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3088. Min Act: -0.0002

Data Index: 42617 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3115. Min Act: -0.0002

Data Index: 774907 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3110. Min Act: -0.0002

Data Index: 640371 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.2905. Min Act: -0.0002

Data Index: 1141321 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.4525. Min Range: -0.4525

Max Act: 0.3084. Min Act: -0.0001

Data Index: 694337 (C4 (Web Text))

Max Activating Token Index: 391