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

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

Neuron 435 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.7645. Min Act: -0.0000

Data Index: 251396 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.7422. Min Act: -0.0000

Data Index: 50717 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.6116. Min Act: -0.0000

Data Index: 1059054 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.6190. Min Act: -0.0000

Data Index: 616768 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.5715. Min Act: -0.0000

Data Index: 620975 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.5953. Min Act: -0.0000

Data Index: 834138 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1173177 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.5219. Min Act: -0.0000

Data Index: 1159841 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1268497 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.5245. Min Act: -0.0000

Data Index: 1174615 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.5125. Min Act: -0.0000

Data Index: 388801 (C4 (Web Text))

Max Activating Token Index: 815

Text #11

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.5108. Min Act: -0.0000

Data Index: 48447 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.4932. Min Act: -0.0000

Data Index: 137432 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.4417. Min Act: -0.0000

Data Index: 742911 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.4318. Min Act: -0.0000

Data Index: 197203 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.4724. Min Act: -0.0000

Data Index: 67996 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1053199 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.4214. Min Act: -0.0000

Data Index: 872181 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.4078. Min Act: -0.0000

Data Index: 935787 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.7645. Min Range: -0.7645

Max Act: 0.4788. Min Act: -0.0000

Data Index: 368116 (C4 (Web Text))

Max Activating Token Index: 681