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

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

Neuron 3903 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0081. Min Range: -4.0081

Max Act: 4.0081. Min Act: -0.0000

Data Index: 1271077 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.9273. Min Act: -0.0001

Data Index: 1008041 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.6848. Min Act: -0.0000

Data Index: 607684 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.4984. Min Act: -0.0000

Data Index: 632462 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.4501. Min Act: -0.0001

Data Index: 1235461 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.5613. Min Act: -0.0000

Data Index: 501632 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.5480. Min Act: -0.0001

Data Index: 1249954 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.5694. Min Act: -0.0000

Data Index: 664981 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.3503. Min Act: -0.0000

Data Index: 255680 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.4584. Min Act: -0.0000

Data Index: 1256955 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.4396. Min Act: -0.0001

Data Index: 319511 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.4172. Min Act: -0.0001

Data Index: 325652 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.0721. Min Act: -0.0001

Data Index: 385316 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.1409. Min Act: -0.0000

Data Index: 310763 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.2975. Min Act: -0.0000

Data Index: 315338 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.4198. Min Act: -0.0000

Data Index: 374877 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.0807. Min Act: -0.0000

Data Index: 1319446 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 4.0081. Min Range: -4.0081

Max Act: 2.8619. Min Act: -0.0000

Data Index: 299638 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 4.0081. Min Range: -4.0081

Max Act: 3.1217. Min Act: -0.0001

Data Index: 828352 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 4.0081. Min Range: -4.0081

Max Act: 2.8173. Min Act: -0.0000

Data Index: 684558 (C4 (Web Text))

Max Activating Token Index: 243